Created
September 5, 2024 19:24
-
-
Save qpwo/3e8851960b67190ea08a5e06edfbd03f to your computer and use it in GitHub Desktop.
llama 3.1 405b all weight shapes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name | numel | dtype | shape | path | |
|---|---|---|---|---|---|
| lm_head.weight | 2_101_346_304 | torch.bfloat16 | (128256, 16384) | model-00191-of-00191.safetensors | |
| model.embed_tokens.weight | 2_101_346_304 | torch.bfloat16 | (128256, 16384) | model-00001-of-00191.safetensors | |
| model.layers.0.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00003-of-00191.safetensors | |
| model.layers.0.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00003-of-00191.safetensors | |
| model.layers.0.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00002-of-00191.safetensors | |
| model.layers.0.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00002-of-00191.safetensors | |
| model.layers.0.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00003-of-00191.safetensors | |
| model.layers.0.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00001-of-00191.safetensors | |
| model.layers.0.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00002-of-00191.safetensors | |
| model.layers.0.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00001-of-00191.safetensors | |
| model.layers.0.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00001-of-00191.safetensors | |
| model.layers.1.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00004-of-00191.safetensors | |
| model.layers.1.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00004-of-00191.safetensors | |
| model.layers.1.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00003-of-00191.safetensors | |
| model.layers.1.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00004-of-00191.safetensors | |
| model.layers.1.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00004-of-00191.safetensors | |
| model.layers.1.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00003-of-00191.safetensors | |
| model.layers.1.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00003-of-00191.safetensors | |
| model.layers.1.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00003-of-00191.safetensors | |
| model.layers.1.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00003-of-00191.safetensors | |
| model.layers.2.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00006-of-00191.safetensors | |
| model.layers.2.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00006-of-00191.safetensors | |
| model.layers.2.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00005-of-00191.safetensors | |
| model.layers.2.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00005-of-00191.safetensors | |
| model.layers.2.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00006-of-00191.safetensors | |
| model.layers.2.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00004-of-00191.safetensors | |
| model.layers.2.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00004-of-00191.safetensors | |
| model.layers.2.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00004-of-00191.safetensors | |
| model.layers.2.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00004-of-00191.safetensors | |
| model.layers.3.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00007-of-00191.safetensors | |
| model.layers.3.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00007-of-00191.safetensors | |
| model.layers.3.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00006-of-00191.safetensors | |
| model.layers.3.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00007-of-00191.safetensors | |
| model.layers.3.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00007-of-00191.safetensors | |
| model.layers.3.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00006-of-00191.safetensors | |
| model.layers.3.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00006-of-00191.safetensors | |
| model.layers.3.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00006-of-00191.safetensors | |
| model.layers.3.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00006-of-00191.safetensors | |
| model.layers.4.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00009-of-00191.safetensors | |
| model.layers.4.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00009-of-00191.safetensors | |
| model.layers.4.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00008-of-00191.safetensors | |
| model.layers.4.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00008-of-00191.safetensors | |
| model.layers.4.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00009-of-00191.safetensors | |
| model.layers.4.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00007-of-00191.safetensors | |
| model.layers.4.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00007-of-00191.safetensors | |
| model.layers.4.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00007-of-00191.safetensors | |
| model.layers.4.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00007-of-00191.safetensors | |
| model.layers.5.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00010-of-00191.safetensors | |
| model.layers.5.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00010-of-00191.safetensors | |
| model.layers.5.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00009-of-00191.safetensors | |
| model.layers.5.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00010-of-00191.safetensors | |
| model.layers.5.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00010-of-00191.safetensors | |
| model.layers.5.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00009-of-00191.safetensors | |
| model.layers.5.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00009-of-00191.safetensors | |
| model.layers.5.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00009-of-00191.safetensors | |
| model.layers.5.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00009-of-00191.safetensors | |
| model.layers.6.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00012-of-00191.safetensors | |
| model.layers.6.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00012-of-00191.safetensors | |
| model.layers.6.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00011-of-00191.safetensors | |
| model.layers.6.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00011-of-00191.safetensors | |
| model.layers.6.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00012-of-00191.safetensors | |
| model.layers.6.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00010-of-00191.safetensors | |
| model.layers.6.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00010-of-00191.safetensors | |
| model.layers.6.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00010-of-00191.safetensors | |
| model.layers.6.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00010-of-00191.safetensors | |
| model.layers.7.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00013-of-00191.safetensors | |
| model.layers.7.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00013-of-00191.safetensors | |
| model.layers.7.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00012-of-00191.safetensors | |
| model.layers.7.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00013-of-00191.safetensors | |
| model.layers.7.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00013-of-00191.safetensors | |
| model.layers.7.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00012-of-00191.safetensors | |
| model.layers.7.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00012-of-00191.safetensors | |
| model.layers.7.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00012-of-00191.safetensors | |
| model.layers.7.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00012-of-00191.safetensors | |
| model.layers.8.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00015-of-00191.safetensors | |
| model.layers.8.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00015-of-00191.safetensors | |
| model.layers.8.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00014-of-00191.safetensors | |
| model.layers.8.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00014-of-00191.safetensors | |
| model.layers.8.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00015-of-00191.safetensors | |
| model.layers.8.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00013-of-00191.safetensors | |
| model.layers.8.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00013-of-00191.safetensors | |
| model.layers.8.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00013-of-00191.safetensors | |
| model.layers.8.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00013-of-00191.safetensors | |
| model.layers.9.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00016-of-00191.safetensors | |
| model.layers.9.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00016-of-00191.safetensors | |
| model.layers.9.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00015-of-00191.safetensors | |
| model.layers.9.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00016-of-00191.safetensors | |
| model.layers.9.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00016-of-00191.safetensors | |
| model.layers.9.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00015-of-00191.safetensors | |
| model.layers.9.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00015-of-00191.safetensors | |
| model.layers.9.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00015-of-00191.safetensors | |
| model.layers.9.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00015-of-00191.safetensors | |
| model.layers.10.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00018-of-00191.safetensors | |
| model.layers.10.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00018-of-00191.safetensors | |
| model.layers.10.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00017-of-00191.safetensors | |
| model.layers.10.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00017-of-00191.safetensors | |
| model.layers.10.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00018-of-00191.safetensors | |
| model.layers.10.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00016-of-00191.safetensors | |
| model.layers.10.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00016-of-00191.safetensors | |
| model.layers.10.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00016-of-00191.safetensors | |
| model.layers.10.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00016-of-00191.safetensors | |
| model.layers.11.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00019-of-00191.safetensors | |
| model.layers.11.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00019-of-00191.safetensors | |
| model.layers.11.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00018-of-00191.safetensors | |
| model.layers.11.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00019-of-00191.safetensors | |
| model.layers.11.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00019-of-00191.safetensors | |
| model.layers.11.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00018-of-00191.safetensors | |
| model.layers.11.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00018-of-00191.safetensors | |
| model.layers.11.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00018-of-00191.safetensors | |
| model.layers.11.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00018-of-00191.safetensors | |
| model.layers.12.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00021-of-00191.safetensors | |
| model.layers.12.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00021-of-00191.safetensors | |
| model.layers.12.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00020-of-00191.safetensors | |
| model.layers.12.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00020-of-00191.safetensors | |
| model.layers.12.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00021-of-00191.safetensors | |
| model.layers.12.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00019-of-00191.safetensors | |
| model.layers.12.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00019-of-00191.safetensors | |
| model.layers.12.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00019-of-00191.safetensors | |
| model.layers.12.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00019-of-00191.safetensors | |
| model.layers.13.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00022-of-00191.safetensors | |
| model.layers.13.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00022-of-00191.safetensors | |
| model.layers.13.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00021-of-00191.safetensors | |
| model.layers.13.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00022-of-00191.safetensors | |
| model.layers.13.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00022-of-00191.safetensors | |
| model.layers.13.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00021-of-00191.safetensors | |
| model.layers.13.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00021-of-00191.safetensors | |
| model.layers.13.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00021-of-00191.safetensors | |
| model.layers.13.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00021-of-00191.safetensors | |
| model.layers.14.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00024-of-00191.safetensors | |
| model.layers.14.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00024-of-00191.safetensors | |
| model.layers.14.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00023-of-00191.safetensors | |
| model.layers.14.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00023-of-00191.safetensors | |
| model.layers.14.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00024-of-00191.safetensors | |
| model.layers.14.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00022-of-00191.safetensors | |
| model.layers.14.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00022-of-00191.safetensors | |
| model.layers.14.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00022-of-00191.safetensors | |
| model.layers.14.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00022-of-00191.safetensors | |
| model.layers.15.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00025-of-00191.safetensors | |
| model.layers.15.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00025-of-00191.safetensors | |
| model.layers.15.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00024-of-00191.safetensors | |
| model.layers.15.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00025-of-00191.safetensors | |
| model.layers.15.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00025-of-00191.safetensors | |
| model.layers.15.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00024-of-00191.safetensors | |
| model.layers.15.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00024-of-00191.safetensors | |
| model.layers.15.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00024-of-00191.safetensors | |
| model.layers.15.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00024-of-00191.safetensors | |
| model.layers.16.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00027-of-00191.safetensors | |
| model.layers.16.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00027-of-00191.safetensors | |
| model.layers.16.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00026-of-00191.safetensors | |
| model.layers.16.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00026-of-00191.safetensors | |
| model.layers.16.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00027-of-00191.safetensors | |
| model.layers.16.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00025-of-00191.safetensors | |
| model.layers.16.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00025-of-00191.safetensors | |
| model.layers.16.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00025-of-00191.safetensors | |
| model.layers.16.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00025-of-00191.safetensors | |
| model.layers.17.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00028-of-00191.safetensors | |
| model.layers.17.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00028-of-00191.safetensors | |
| model.layers.17.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00027-of-00191.safetensors | |
| model.layers.17.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00028-of-00191.safetensors | |
| model.layers.17.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00028-of-00191.safetensors | |
| model.layers.17.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00027-of-00191.safetensors | |
| model.layers.17.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00027-of-00191.safetensors | |
| model.layers.17.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00027-of-00191.safetensors | |
| model.layers.17.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00027-of-00191.safetensors | |
| model.layers.18.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00030-of-00191.safetensors | |
| model.layers.18.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00030-of-00191.safetensors | |
| model.layers.18.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00029-of-00191.safetensors | |
| model.layers.18.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00029-of-00191.safetensors | |
| model.layers.18.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00030-of-00191.safetensors | |
| model.layers.18.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00028-of-00191.safetensors | |
| model.layers.18.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00028-of-00191.safetensors | |
| model.layers.18.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00028-of-00191.safetensors | |
| model.layers.18.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00028-of-00191.safetensors | |
| model.layers.19.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00031-of-00191.safetensors | |
| model.layers.19.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00031-of-00191.safetensors | |
| model.layers.19.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00030-of-00191.safetensors | |
| model.layers.19.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00031-of-00191.safetensors | |
| model.layers.19.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00031-of-00191.safetensors | |
| model.layers.19.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00030-of-00191.safetensors | |
| model.layers.19.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00030-of-00191.safetensors | |
| model.layers.19.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00030-of-00191.safetensors | |
| model.layers.19.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00030-of-00191.safetensors | |
| model.layers.20.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00033-of-00191.safetensors | |
| model.layers.20.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00033-of-00191.safetensors | |
| model.layers.20.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00032-of-00191.safetensors | |
| model.layers.20.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00032-of-00191.safetensors | |
| model.layers.20.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00033-of-00191.safetensors | |
| model.layers.20.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00031-of-00191.safetensors | |
| model.layers.20.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00031-of-00191.safetensors | |
| model.layers.20.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00031-of-00191.safetensors | |
| model.layers.20.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00031-of-00191.safetensors | |
| model.layers.21.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00034-of-00191.safetensors | |
| model.layers.21.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00034-of-00191.safetensors | |
| model.layers.21.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00033-of-00191.safetensors | |
| model.layers.21.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00034-of-00191.safetensors | |
| model.layers.21.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00034-of-00191.safetensors | |
| model.layers.21.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00033-of-00191.safetensors | |
| model.layers.21.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00033-of-00191.safetensors | |
| model.layers.21.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00033-of-00191.safetensors | |
| model.layers.21.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00033-of-00191.safetensors | |
| model.layers.22.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00036-of-00191.safetensors | |
| model.layers.22.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00036-of-00191.safetensors | |
| model.layers.22.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00035-of-00191.safetensors | |
| model.layers.22.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00035-of-00191.safetensors | |
| model.layers.22.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00036-of-00191.safetensors | |
| model.layers.22.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00034-of-00191.safetensors | |
| model.layers.22.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00034-of-00191.safetensors | |
| model.layers.22.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00034-of-00191.safetensors | |
| model.layers.22.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00034-of-00191.safetensors | |
| model.layers.23.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00037-of-00191.safetensors | |
| model.layers.23.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00037-of-00191.safetensors | |
| model.layers.23.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00036-of-00191.safetensors | |
| model.layers.23.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00037-of-00191.safetensors | |
| model.layers.23.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00037-of-00191.safetensors | |
| model.layers.23.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00036-of-00191.safetensors | |
| model.layers.23.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00036-of-00191.safetensors | |
| model.layers.23.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00036-of-00191.safetensors | |
| model.layers.23.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00036-of-00191.safetensors | |
| model.layers.24.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00039-of-00191.safetensors | |
| model.layers.24.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00039-of-00191.safetensors | |
| model.layers.24.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00038-of-00191.safetensors | |
| model.layers.24.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00038-of-00191.safetensors | |
| model.layers.24.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00039-of-00191.safetensors | |
| model.layers.24.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00037-of-00191.safetensors | |
| model.layers.24.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00037-of-00191.safetensors | |
| model.layers.24.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00037-of-00191.safetensors | |
| model.layers.24.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00037-of-00191.safetensors | |
| model.layers.25.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00040-of-00191.safetensors | |
| model.layers.25.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00040-of-00191.safetensors | |
| model.layers.25.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00039-of-00191.safetensors | |
| model.layers.25.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00040-of-00191.safetensors | |
| model.layers.25.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00040-of-00191.safetensors | |
| model.layers.25.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00039-of-00191.safetensors | |
| model.layers.25.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00039-of-00191.safetensors | |
| model.layers.25.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00039-of-00191.safetensors | |
| model.layers.25.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00039-of-00191.safetensors | |
| model.layers.26.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00042-of-00191.safetensors | |
| model.layers.26.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00042-of-00191.safetensors | |
| model.layers.26.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00041-of-00191.safetensors | |
| model.layers.26.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00041-of-00191.safetensors | |
| model.layers.26.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00042-of-00191.safetensors | |
| model.layers.26.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00040-of-00191.safetensors | |
| model.layers.26.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00040-of-00191.safetensors | |
| model.layers.26.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00040-of-00191.safetensors | |
| model.layers.26.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00040-of-00191.safetensors | |
| model.layers.27.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00043-of-00191.safetensors | |
| model.layers.27.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00043-of-00191.safetensors | |
| model.layers.27.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00042-of-00191.safetensors | |
| model.layers.27.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00043-of-00191.safetensors | |
| model.layers.27.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00043-of-00191.safetensors | |
| model.layers.27.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00042-of-00191.safetensors | |
| model.layers.27.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00042-of-00191.safetensors | |
| model.layers.27.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00042-of-00191.safetensors | |
| model.layers.27.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00042-of-00191.safetensors | |
| model.layers.28.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00045-of-00191.safetensors | |
| model.layers.28.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00045-of-00191.safetensors | |
| model.layers.28.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00044-of-00191.safetensors | |
| model.layers.28.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00044-of-00191.safetensors | |
| model.layers.28.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00045-of-00191.safetensors | |
| model.layers.28.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00043-of-00191.safetensors | |
| model.layers.28.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00043-of-00191.safetensors | |
| model.layers.28.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00043-of-00191.safetensors | |
| model.layers.28.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00043-of-00191.safetensors | |
| model.layers.29.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00046-of-00191.safetensors | |
| model.layers.29.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00046-of-00191.safetensors | |
| model.layers.29.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00045-of-00191.safetensors | |
| model.layers.29.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00046-of-00191.safetensors | |
| model.layers.29.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00046-of-00191.safetensors | |
| model.layers.29.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00045-of-00191.safetensors | |
| model.layers.29.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00045-of-00191.safetensors | |
| model.layers.29.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00045-of-00191.safetensors | |
| model.layers.29.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00045-of-00191.safetensors | |
| model.layers.30.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00048-of-00191.safetensors | |
| model.layers.30.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00048-of-00191.safetensors | |
| model.layers.30.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00047-of-00191.safetensors | |
| model.layers.30.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00047-of-00191.safetensors | |
| model.layers.30.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00048-of-00191.safetensors | |
| model.layers.30.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00046-of-00191.safetensors | |
| model.layers.30.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00046-of-00191.safetensors | |
| model.layers.30.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00046-of-00191.safetensors | |
| model.layers.30.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00046-of-00191.safetensors | |
| model.layers.31.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00049-of-00191.safetensors | |
| model.layers.31.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00049-of-00191.safetensors | |
| model.layers.31.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00048-of-00191.safetensors | |
| model.layers.31.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00049-of-00191.safetensors | |
| model.layers.31.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00049-of-00191.safetensors | |
| model.layers.31.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00048-of-00191.safetensors | |
| model.layers.31.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00048-of-00191.safetensors | |
| model.layers.31.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00048-of-00191.safetensors | |
| model.layers.31.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00048-of-00191.safetensors | |
| model.layers.32.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00051-of-00191.safetensors | |
| model.layers.32.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00051-of-00191.safetensors | |
| model.layers.32.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00050-of-00191.safetensors | |
| model.layers.32.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00050-of-00191.safetensors | |
| model.layers.32.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00051-of-00191.safetensors | |
| model.layers.32.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00049-of-00191.safetensors | |
| model.layers.32.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00049-of-00191.safetensors | |
| model.layers.32.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00049-of-00191.safetensors | |
| model.layers.32.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00049-of-00191.safetensors | |
| model.layers.33.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00052-of-00191.safetensors | |
| model.layers.33.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00052-of-00191.safetensors | |
| model.layers.33.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00051-of-00191.safetensors | |
| model.layers.33.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00052-of-00191.safetensors | |
| model.layers.33.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00052-of-00191.safetensors | |
| model.layers.33.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00051-of-00191.safetensors | |
| model.layers.33.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00051-of-00191.safetensors | |
| model.layers.33.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00051-of-00191.safetensors | |
| model.layers.33.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00051-of-00191.safetensors | |
| model.layers.34.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00054-of-00191.safetensors | |
| model.layers.34.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00054-of-00191.safetensors | |
| model.layers.34.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00053-of-00191.safetensors | |
| model.layers.34.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00053-of-00191.safetensors | |
| model.layers.34.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00054-of-00191.safetensors | |
| model.layers.34.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00052-of-00191.safetensors | |
| model.layers.34.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00052-of-00191.safetensors | |
| model.layers.34.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00052-of-00191.safetensors | |
| model.layers.34.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00052-of-00191.safetensors | |
| model.layers.35.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00055-of-00191.safetensors | |
| model.layers.35.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00055-of-00191.safetensors | |
| model.layers.35.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00054-of-00191.safetensors | |
| model.layers.35.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00055-of-00191.safetensors | |
| model.layers.35.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00055-of-00191.safetensors | |
| model.layers.35.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00054-of-00191.safetensors | |
| model.layers.35.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00054-of-00191.safetensors | |
| model.layers.35.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00054-of-00191.safetensors | |
| model.layers.35.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00054-of-00191.safetensors | |
| model.layers.36.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00057-of-00191.safetensors | |
| model.layers.36.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00057-of-00191.safetensors | |
| model.layers.36.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00056-of-00191.safetensors | |
| model.layers.36.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00056-of-00191.safetensors | |
| model.layers.36.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00057-of-00191.safetensors | |
| model.layers.36.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00055-of-00191.safetensors | |
| model.layers.36.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00055-of-00191.safetensors | |
| model.layers.36.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00055-of-00191.safetensors | |
| model.layers.36.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00055-of-00191.safetensors | |
| model.layers.37.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00058-of-00191.safetensors | |
| model.layers.37.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00058-of-00191.safetensors | |
| model.layers.37.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00057-of-00191.safetensors | |
| model.layers.37.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00058-of-00191.safetensors | |
| model.layers.37.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00058-of-00191.safetensors | |
| model.layers.37.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00057-of-00191.safetensors | |
| model.layers.37.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00057-of-00191.safetensors | |
| model.layers.37.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00057-of-00191.safetensors | |
| model.layers.37.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00057-of-00191.safetensors | |
| model.layers.38.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00060-of-00191.safetensors | |
| model.layers.38.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00060-of-00191.safetensors | |
| model.layers.38.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00059-of-00191.safetensors | |
| model.layers.38.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00059-of-00191.safetensors | |
| model.layers.38.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00060-of-00191.safetensors | |
| model.layers.38.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00058-of-00191.safetensors | |
| model.layers.38.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00058-of-00191.safetensors | |
| model.layers.38.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00058-of-00191.safetensors | |
| model.layers.38.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00058-of-00191.safetensors | |
| model.layers.39.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00061-of-00191.safetensors | |
| model.layers.39.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00061-of-00191.safetensors | |
| model.layers.39.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00060-of-00191.safetensors | |
| model.layers.39.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00061-of-00191.safetensors | |
| model.layers.39.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00061-of-00191.safetensors | |
| model.layers.39.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00060-of-00191.safetensors | |
| model.layers.39.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00060-of-00191.safetensors | |
| model.layers.39.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00060-of-00191.safetensors | |
| model.layers.39.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00060-of-00191.safetensors | |
| model.layers.40.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00063-of-00191.safetensors | |
| model.layers.40.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00063-of-00191.safetensors | |
| model.layers.40.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00062-of-00191.safetensors | |
| model.layers.40.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00062-of-00191.safetensors | |
| model.layers.40.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00063-of-00191.safetensors | |
| model.layers.40.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00061-of-00191.safetensors | |
| model.layers.40.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00061-of-00191.safetensors | |
| model.layers.40.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00061-of-00191.safetensors | |
| model.layers.40.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00061-of-00191.safetensors | |
| model.layers.41.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00064-of-00191.safetensors | |
| model.layers.41.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00064-of-00191.safetensors | |
| model.layers.41.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00063-of-00191.safetensors | |
| model.layers.41.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00064-of-00191.safetensors | |
| model.layers.41.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00064-of-00191.safetensors | |
| model.layers.41.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00063-of-00191.safetensors | |
| model.layers.41.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00063-of-00191.safetensors | |
| model.layers.41.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00063-of-00191.safetensors | |
| model.layers.41.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00063-of-00191.safetensors | |
| model.layers.42.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00066-of-00191.safetensors | |
| model.layers.42.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00066-of-00191.safetensors | |
| model.layers.42.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00065-of-00191.safetensors | |
| model.layers.42.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00065-of-00191.safetensors | |
| model.layers.42.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00066-of-00191.safetensors | |
| model.layers.42.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00064-of-00191.safetensors | |
| model.layers.42.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00064-of-00191.safetensors | |
| model.layers.42.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00064-of-00191.safetensors | |
| model.layers.42.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00064-of-00191.safetensors | |
| model.layers.43.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00067-of-00191.safetensors | |
| model.layers.43.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00067-of-00191.safetensors | |
| model.layers.43.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00066-of-00191.safetensors | |
| model.layers.43.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00067-of-00191.safetensors | |
| model.layers.43.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00067-of-00191.safetensors | |
| model.layers.43.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00066-of-00191.safetensors | |
| model.layers.43.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00066-of-00191.safetensors | |
| model.layers.43.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00066-of-00191.safetensors | |
| model.layers.43.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00066-of-00191.safetensors | |
| model.layers.44.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00069-of-00191.safetensors | |
| model.layers.44.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00069-of-00191.safetensors | |
| model.layers.44.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00068-of-00191.safetensors | |
| model.layers.44.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00068-of-00191.safetensors | |
| model.layers.44.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00069-of-00191.safetensors | |
| model.layers.44.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00067-of-00191.safetensors | |
| model.layers.44.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00067-of-00191.safetensors | |
| model.layers.44.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00067-of-00191.safetensors | |
| model.layers.44.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00067-of-00191.safetensors | |
| model.layers.45.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00070-of-00191.safetensors | |
| model.layers.45.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00070-of-00191.safetensors | |
| model.layers.45.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00069-of-00191.safetensors | |
| model.layers.45.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00070-of-00191.safetensors | |
| model.layers.45.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00070-of-00191.safetensors | |
| model.layers.45.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00069-of-00191.safetensors | |
| model.layers.45.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00069-of-00191.safetensors | |
| model.layers.45.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00069-of-00191.safetensors | |
| model.layers.45.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00069-of-00191.safetensors | |
| model.layers.46.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00072-of-00191.safetensors | |
| model.layers.46.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00072-of-00191.safetensors | |
| model.layers.46.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00071-of-00191.safetensors | |
| model.layers.46.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00071-of-00191.safetensors | |
| model.layers.46.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00072-of-00191.safetensors | |
| model.layers.46.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00070-of-00191.safetensors | |
| model.layers.46.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00070-of-00191.safetensors | |
| model.layers.46.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00070-of-00191.safetensors | |
| model.layers.46.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00070-of-00191.safetensors | |
| model.layers.47.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00073-of-00191.safetensors | |
| model.layers.47.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00073-of-00191.safetensors | |
| model.layers.47.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00072-of-00191.safetensors | |
| model.layers.47.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00073-of-00191.safetensors | |
| model.layers.47.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00073-of-00191.safetensors | |
| model.layers.47.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00072-of-00191.safetensors | |
| model.layers.47.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00072-of-00191.safetensors | |
| model.layers.47.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00072-of-00191.safetensors | |
| model.layers.47.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00072-of-00191.safetensors | |
| model.layers.48.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00075-of-00191.safetensors | |
| model.layers.48.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00075-of-00191.safetensors | |
| model.layers.48.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00074-of-00191.safetensors | |
| model.layers.48.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00074-of-00191.safetensors | |
| model.layers.48.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00075-of-00191.safetensors | |
| model.layers.48.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00073-of-00191.safetensors | |
| model.layers.48.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00073-of-00191.safetensors | |
| model.layers.48.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00073-of-00191.safetensors | |
| model.layers.48.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00073-of-00191.safetensors | |
| model.layers.49.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00076-of-00191.safetensors | |
| model.layers.49.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00076-of-00191.safetensors | |
| model.layers.49.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00075-of-00191.safetensors | |
| model.layers.49.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00076-of-00191.safetensors | |
| model.layers.49.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00076-of-00191.safetensors | |
| model.layers.49.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00075-of-00191.safetensors | |
| model.layers.49.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00075-of-00191.safetensors | |
| model.layers.49.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00075-of-00191.safetensors | |
| model.layers.49.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00075-of-00191.safetensors | |
| model.layers.50.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00078-of-00191.safetensors | |
| model.layers.50.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00078-of-00191.safetensors | |
| model.layers.50.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00077-of-00191.safetensors | |
| model.layers.50.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00077-of-00191.safetensors | |
| model.layers.50.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00078-of-00191.safetensors | |
| model.layers.50.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00076-of-00191.safetensors | |
| model.layers.50.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00076-of-00191.safetensors | |
| model.layers.50.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00076-of-00191.safetensors | |
| model.layers.50.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00076-of-00191.safetensors | |
| model.layers.51.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00079-of-00191.safetensors | |
| model.layers.51.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00079-of-00191.safetensors | |
| model.layers.51.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00078-of-00191.safetensors | |
| model.layers.51.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00079-of-00191.safetensors | |
| model.layers.51.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00079-of-00191.safetensors | |
| model.layers.51.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00078-of-00191.safetensors | |
| model.layers.51.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00078-of-00191.safetensors | |
| model.layers.51.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00078-of-00191.safetensors | |
| model.layers.51.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00078-of-00191.safetensors | |
| model.layers.52.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00081-of-00191.safetensors | |
| model.layers.52.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00081-of-00191.safetensors | |
| model.layers.52.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00080-of-00191.safetensors | |
| model.layers.52.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00080-of-00191.safetensors | |
| model.layers.52.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00081-of-00191.safetensors | |
| model.layers.52.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00079-of-00191.safetensors | |
| model.layers.52.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00079-of-00191.safetensors | |
| model.layers.52.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00079-of-00191.safetensors | |
| model.layers.52.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00079-of-00191.safetensors | |
| model.layers.53.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00082-of-00191.safetensors | |
| model.layers.53.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00082-of-00191.safetensors | |
| model.layers.53.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00081-of-00191.safetensors | |
| model.layers.53.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00082-of-00191.safetensors | |
| model.layers.53.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00082-of-00191.safetensors | |
| model.layers.53.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00081-of-00191.safetensors | |
| model.layers.53.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00081-of-00191.safetensors | |
| model.layers.53.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00081-of-00191.safetensors | |
| model.layers.53.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00081-of-00191.safetensors | |
| model.layers.54.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00084-of-00191.safetensors | |
| model.layers.54.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00084-of-00191.safetensors | |
| model.layers.54.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00083-of-00191.safetensors | |
| model.layers.54.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00083-of-00191.safetensors | |
| model.layers.54.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00084-of-00191.safetensors | |
| model.layers.54.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00082-of-00191.safetensors | |
| model.layers.54.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00082-of-00191.safetensors | |
| model.layers.54.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00082-of-00191.safetensors | |
| model.layers.54.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00082-of-00191.safetensors | |
| model.layers.55.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00085-of-00191.safetensors | |
| model.layers.55.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00085-of-00191.safetensors | |
| model.layers.55.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00084-of-00191.safetensors | |
| model.layers.55.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00085-of-00191.safetensors | |
| model.layers.55.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00085-of-00191.safetensors | |
| model.layers.55.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00084-of-00191.safetensors | |
| model.layers.55.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00084-of-00191.safetensors | |
| model.layers.55.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00084-of-00191.safetensors | |
| model.layers.55.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00084-of-00191.safetensors | |
| model.layers.56.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00087-of-00191.safetensors | |
| model.layers.56.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00087-of-00191.safetensors | |
| model.layers.56.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00086-of-00191.safetensors | |
| model.layers.56.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00086-of-00191.safetensors | |
| model.layers.56.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00087-of-00191.safetensors | |
| model.layers.56.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00085-of-00191.safetensors | |
| model.layers.56.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00085-of-00191.safetensors | |
| model.layers.56.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00085-of-00191.safetensors | |
| model.layers.56.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00085-of-00191.safetensors | |
| model.layers.57.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00088-of-00191.safetensors | |
| model.layers.57.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00088-of-00191.safetensors | |
| model.layers.57.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00087-of-00191.safetensors | |
| model.layers.57.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00088-of-00191.safetensors | |
| model.layers.57.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00088-of-00191.safetensors | |
| model.layers.57.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00087-of-00191.safetensors | |
| model.layers.57.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00087-of-00191.safetensors | |
| model.layers.57.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00087-of-00191.safetensors | |
| model.layers.57.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00087-of-00191.safetensors | |
| model.layers.58.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00090-of-00191.safetensors | |
| model.layers.58.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00090-of-00191.safetensors | |
| model.layers.58.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00089-of-00191.safetensors | |
| model.layers.58.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00089-of-00191.safetensors | |
| model.layers.58.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00090-of-00191.safetensors | |
| model.layers.58.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00088-of-00191.safetensors | |
| model.layers.58.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00088-of-00191.safetensors | |
| model.layers.58.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00088-of-00191.safetensors | |
| model.layers.58.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00088-of-00191.safetensors | |
| model.layers.59.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00091-of-00191.safetensors | |
| model.layers.59.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00091-of-00191.safetensors | |
| model.layers.59.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00090-of-00191.safetensors | |
| model.layers.59.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00091-of-00191.safetensors | |
| model.layers.59.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00091-of-00191.safetensors | |
| model.layers.59.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00090-of-00191.safetensors | |
| model.layers.59.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00090-of-00191.safetensors | |
| model.layers.59.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00090-of-00191.safetensors | |
| model.layers.59.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00090-of-00191.safetensors | |
| model.layers.60.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00093-of-00191.safetensors | |
| model.layers.60.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00093-of-00191.safetensors | |
| model.layers.60.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00092-of-00191.safetensors | |
| model.layers.60.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00092-of-00191.safetensors | |
| model.layers.60.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00093-of-00191.safetensors | |
| model.layers.60.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00091-of-00191.safetensors | |
| model.layers.60.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00091-of-00191.safetensors | |
| model.layers.60.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00091-of-00191.safetensors | |
| model.layers.60.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00091-of-00191.safetensors | |
| model.layers.61.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00094-of-00191.safetensors | |
| model.layers.61.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00094-of-00191.safetensors | |
| model.layers.61.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00093-of-00191.safetensors | |
| model.layers.61.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00094-of-00191.safetensors | |
| model.layers.61.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00094-of-00191.safetensors | |
| model.layers.61.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00093-of-00191.safetensors | |
| model.layers.61.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00093-of-00191.safetensors | |
| model.layers.61.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00093-of-00191.safetensors | |
| model.layers.61.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00093-of-00191.safetensors | |
| model.layers.62.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00096-of-00191.safetensors | |
| model.layers.62.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00096-of-00191.safetensors | |
| model.layers.62.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00095-of-00191.safetensors | |
| model.layers.62.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00095-of-00191.safetensors | |
| model.layers.62.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00096-of-00191.safetensors | |
| model.layers.62.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00094-of-00191.safetensors | |
| model.layers.62.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00094-of-00191.safetensors | |
| model.layers.62.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00094-of-00191.safetensors | |
| model.layers.62.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00094-of-00191.safetensors | |
| model.layers.63.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00097-of-00191.safetensors | |
| model.layers.63.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00097-of-00191.safetensors | |
| model.layers.63.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00096-of-00191.safetensors | |
| model.layers.63.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00097-of-00191.safetensors | |
| model.layers.63.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00097-of-00191.safetensors | |
| model.layers.63.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00096-of-00191.safetensors | |
| model.layers.63.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00096-of-00191.safetensors | |
| model.layers.63.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00096-of-00191.safetensors | |
| model.layers.63.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00096-of-00191.safetensors | |
| model.layers.64.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00099-of-00191.safetensors | |
| model.layers.64.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00099-of-00191.safetensors | |
| model.layers.64.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00098-of-00191.safetensors | |
| model.layers.64.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00098-of-00191.safetensors | |
| model.layers.64.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00099-of-00191.safetensors | |
| model.layers.64.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00097-of-00191.safetensors | |
| model.layers.64.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00097-of-00191.safetensors | |
| model.layers.64.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00097-of-00191.safetensors | |
| model.layers.64.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00097-of-00191.safetensors | |
| model.layers.65.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00100-of-00191.safetensors | |
| model.layers.65.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00100-of-00191.safetensors | |
| model.layers.65.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00099-of-00191.safetensors | |
| model.layers.65.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00100-of-00191.safetensors | |
| model.layers.65.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00100-of-00191.safetensors | |
| model.layers.65.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00099-of-00191.safetensors | |
| model.layers.65.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00099-of-00191.safetensors | |
| model.layers.65.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00099-of-00191.safetensors | |
| model.layers.65.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00099-of-00191.safetensors | |
| model.layers.66.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00102-of-00191.safetensors | |
| model.layers.66.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00102-of-00191.safetensors | |
| model.layers.66.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00101-of-00191.safetensors | |
| model.layers.66.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00101-of-00191.safetensors | |
| model.layers.66.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00102-of-00191.safetensors | |
| model.layers.66.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00100-of-00191.safetensors | |
| model.layers.66.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00100-of-00191.safetensors | |
| model.layers.66.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00100-of-00191.safetensors | |
| model.layers.66.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00100-of-00191.safetensors | |
| model.layers.67.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00103-of-00191.safetensors | |
| model.layers.67.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00103-of-00191.safetensors | |
| model.layers.67.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00102-of-00191.safetensors | |
| model.layers.67.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00103-of-00191.safetensors | |
| model.layers.67.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00103-of-00191.safetensors | |
| model.layers.67.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00102-of-00191.safetensors | |
| model.layers.67.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00102-of-00191.safetensors | |
| model.layers.67.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00102-of-00191.safetensors | |
| model.layers.67.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00102-of-00191.safetensors | |
| model.layers.68.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00105-of-00191.safetensors | |
| model.layers.68.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00105-of-00191.safetensors | |
| model.layers.68.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00104-of-00191.safetensors | |
| model.layers.68.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00104-of-00191.safetensors | |
| model.layers.68.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00105-of-00191.safetensors | |
| model.layers.68.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00103-of-00191.safetensors | |
| model.layers.68.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00103-of-00191.safetensors | |
| model.layers.68.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00103-of-00191.safetensors | |
| model.layers.68.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00103-of-00191.safetensors | |
| model.layers.69.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00106-of-00191.safetensors | |
| model.layers.69.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00106-of-00191.safetensors | |
| model.layers.69.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00105-of-00191.safetensors | |
| model.layers.69.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00106-of-00191.safetensors | |
| model.layers.69.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00106-of-00191.safetensors | |
| model.layers.69.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00105-of-00191.safetensors | |
| model.layers.69.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00105-of-00191.safetensors | |
| model.layers.69.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00105-of-00191.safetensors | |
| model.layers.69.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00105-of-00191.safetensors | |
| model.layers.70.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00108-of-00191.safetensors | |
| model.layers.70.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00108-of-00191.safetensors | |
| model.layers.70.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00107-of-00191.safetensors | |
| model.layers.70.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00107-of-00191.safetensors | |
| model.layers.70.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00108-of-00191.safetensors | |
| model.layers.70.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00106-of-00191.safetensors | |
| model.layers.70.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00106-of-00191.safetensors | |
| model.layers.70.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00106-of-00191.safetensors | |
| model.layers.70.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00106-of-00191.safetensors | |
| model.layers.71.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00109-of-00191.safetensors | |
| model.layers.71.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00109-of-00191.safetensors | |
| model.layers.71.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00108-of-00191.safetensors | |
| model.layers.71.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00109-of-00191.safetensors | |
| model.layers.71.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00109-of-00191.safetensors | |
| model.layers.71.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00108-of-00191.safetensors | |
| model.layers.71.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00108-of-00191.safetensors | |
| model.layers.71.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00108-of-00191.safetensors | |
| model.layers.71.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00108-of-00191.safetensors | |
| model.layers.72.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00111-of-00191.safetensors | |
| model.layers.72.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00111-of-00191.safetensors | |
| model.layers.72.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00110-of-00191.safetensors | |
| model.layers.72.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00110-of-00191.safetensors | |
| model.layers.72.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00111-of-00191.safetensors | |
| model.layers.72.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00109-of-00191.safetensors | |
| model.layers.72.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00109-of-00191.safetensors | |
| model.layers.72.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00109-of-00191.safetensors | |
| model.layers.72.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00109-of-00191.safetensors | |
| model.layers.73.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00112-of-00191.safetensors | |
| model.layers.73.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00112-of-00191.safetensors | |
| model.layers.73.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00111-of-00191.safetensors | |
| model.layers.73.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00112-of-00191.safetensors | |
| model.layers.73.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00112-of-00191.safetensors | |
| model.layers.73.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00111-of-00191.safetensors | |
| model.layers.73.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00111-of-00191.safetensors | |
| model.layers.73.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00111-of-00191.safetensors | |
| model.layers.73.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00111-of-00191.safetensors | |
| model.layers.74.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00114-of-00191.safetensors | |
| model.layers.74.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00114-of-00191.safetensors | |
| model.layers.74.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00113-of-00191.safetensors | |
| model.layers.74.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00113-of-00191.safetensors | |
| model.layers.74.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00114-of-00191.safetensors | |
| model.layers.74.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00112-of-00191.safetensors | |
| model.layers.74.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00112-of-00191.safetensors | |
| model.layers.74.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00112-of-00191.safetensors | |
| model.layers.74.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00112-of-00191.safetensors | |
| model.layers.75.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00115-of-00191.safetensors | |
| model.layers.75.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00115-of-00191.safetensors | |
| model.layers.75.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00114-of-00191.safetensors | |
| model.layers.75.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00115-of-00191.safetensors | |
| model.layers.75.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00115-of-00191.safetensors | |
| model.layers.75.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00114-of-00191.safetensors | |
| model.layers.75.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00114-of-00191.safetensors | |
| model.layers.75.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00114-of-00191.safetensors | |
| model.layers.75.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00114-of-00191.safetensors | |
| model.layers.76.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00117-of-00191.safetensors | |
| model.layers.76.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00117-of-00191.safetensors | |
| model.layers.76.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00116-of-00191.safetensors | |
| model.layers.76.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00116-of-00191.safetensors | |
| model.layers.76.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00117-of-00191.safetensors | |
| model.layers.76.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00115-of-00191.safetensors | |
| model.layers.76.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00115-of-00191.safetensors | |
| model.layers.76.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00115-of-00191.safetensors | |
| model.layers.76.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00115-of-00191.safetensors | |
| model.layers.77.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00118-of-00191.safetensors | |
| model.layers.77.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00118-of-00191.safetensors | |
| model.layers.77.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00117-of-00191.safetensors | |
| model.layers.77.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00118-of-00191.safetensors | |
| model.layers.77.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00118-of-00191.safetensors | |
| model.layers.77.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00117-of-00191.safetensors | |
| model.layers.77.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00117-of-00191.safetensors | |
| model.layers.77.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00117-of-00191.safetensors | |
| model.layers.77.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00117-of-00191.safetensors | |
| model.layers.78.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00120-of-00191.safetensors | |
| model.layers.78.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00120-of-00191.safetensors | |
| model.layers.78.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00119-of-00191.safetensors | |
| model.layers.78.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00119-of-00191.safetensors | |
| model.layers.78.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00120-of-00191.safetensors | |
| model.layers.78.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00118-of-00191.safetensors | |
| model.layers.78.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00118-of-00191.safetensors | |
| model.layers.78.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00118-of-00191.safetensors | |
| model.layers.78.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00118-of-00191.safetensors | |
| model.layers.79.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00121-of-00191.safetensors | |
| model.layers.79.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00121-of-00191.safetensors | |
| model.layers.79.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00120-of-00191.safetensors | |
| model.layers.79.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00121-of-00191.safetensors | |
| model.layers.79.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00121-of-00191.safetensors | |
| model.layers.79.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00120-of-00191.safetensors | |
| model.layers.79.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00120-of-00191.safetensors | |
| model.layers.79.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00120-of-00191.safetensors | |
| model.layers.79.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00120-of-00191.safetensors | |
| model.layers.80.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00123-of-00191.safetensors | |
| model.layers.80.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00123-of-00191.safetensors | |
| model.layers.80.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00122-of-00191.safetensors | |
| model.layers.80.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00122-of-00191.safetensors | |
| model.layers.80.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00123-of-00191.safetensors | |
| model.layers.80.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00121-of-00191.safetensors | |
| model.layers.80.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00121-of-00191.safetensors | |
| model.layers.80.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00121-of-00191.safetensors | |
| model.layers.80.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00121-of-00191.safetensors | |
| model.layers.81.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00124-of-00191.safetensors | |
| model.layers.81.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00124-of-00191.safetensors | |
| model.layers.81.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00123-of-00191.safetensors | |
| model.layers.81.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00124-of-00191.safetensors | |
| model.layers.81.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00124-of-00191.safetensors | |
| model.layers.81.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00123-of-00191.safetensors | |
| model.layers.81.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00123-of-00191.safetensors | |
| model.layers.81.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00123-of-00191.safetensors | |
| model.layers.81.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00123-of-00191.safetensors | |
| model.layers.82.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00126-of-00191.safetensors | |
| model.layers.82.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00126-of-00191.safetensors | |
| model.layers.82.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00125-of-00191.safetensors | |
| model.layers.82.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00125-of-00191.safetensors | |
| model.layers.82.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00126-of-00191.safetensors | |
| model.layers.82.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00124-of-00191.safetensors | |
| model.layers.82.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00124-of-00191.safetensors | |
| model.layers.82.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00124-of-00191.safetensors | |
| model.layers.82.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00124-of-00191.safetensors | |
| model.layers.83.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00127-of-00191.safetensors | |
| model.layers.83.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00127-of-00191.safetensors | |
| model.layers.83.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00126-of-00191.safetensors | |
| model.layers.83.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00127-of-00191.safetensors | |
| model.layers.83.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00127-of-00191.safetensors | |
| model.layers.83.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00126-of-00191.safetensors | |
| model.layers.83.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00126-of-00191.safetensors | |
| model.layers.83.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00126-of-00191.safetensors | |
| model.layers.83.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00126-of-00191.safetensors | |
| model.layers.84.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00129-of-00191.safetensors | |
| model.layers.84.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00129-of-00191.safetensors | |
| model.layers.84.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00128-of-00191.safetensors | |
| model.layers.84.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00128-of-00191.safetensors | |
| model.layers.84.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00129-of-00191.safetensors | |
| model.layers.84.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00127-of-00191.safetensors | |
| model.layers.84.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00127-of-00191.safetensors | |
| model.layers.84.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00127-of-00191.safetensors | |
| model.layers.84.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00127-of-00191.safetensors | |
| model.layers.85.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00130-of-00191.safetensors | |
| model.layers.85.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00130-of-00191.safetensors | |
| model.layers.85.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00129-of-00191.safetensors | |
| model.layers.85.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00130-of-00191.safetensors | |
| model.layers.85.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00130-of-00191.safetensors | |
| model.layers.85.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00129-of-00191.safetensors | |
| model.layers.85.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00129-of-00191.safetensors | |
| model.layers.85.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00129-of-00191.safetensors | |
| model.layers.85.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00129-of-00191.safetensors | |
| model.layers.86.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00132-of-00191.safetensors | |
| model.layers.86.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00132-of-00191.safetensors | |
| model.layers.86.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00131-of-00191.safetensors | |
| model.layers.86.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00131-of-00191.safetensors | |
| model.layers.86.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00132-of-00191.safetensors | |
| model.layers.86.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00130-of-00191.safetensors | |
| model.layers.86.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00130-of-00191.safetensors | |
| model.layers.86.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00130-of-00191.safetensors | |
| model.layers.86.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00130-of-00191.safetensors | |
| model.layers.87.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00133-of-00191.safetensors | |
| model.layers.87.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00133-of-00191.safetensors | |
| model.layers.87.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00132-of-00191.safetensors | |
| model.layers.87.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00133-of-00191.safetensors | |
| model.layers.87.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00133-of-00191.safetensors | |
| model.layers.87.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00132-of-00191.safetensors | |
| model.layers.87.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00132-of-00191.safetensors | |
| model.layers.87.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00132-of-00191.safetensors | |
| model.layers.87.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00132-of-00191.safetensors | |
| model.layers.88.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00135-of-00191.safetensors | |
| model.layers.88.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00135-of-00191.safetensors | |
| model.layers.88.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00134-of-00191.safetensors | |
| model.layers.88.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00134-of-00191.safetensors | |
| model.layers.88.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00135-of-00191.safetensors | |
| model.layers.88.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00133-of-00191.safetensors | |
| model.layers.88.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00133-of-00191.safetensors | |
| model.layers.88.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00133-of-00191.safetensors | |
| model.layers.88.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00133-of-00191.safetensors | |
| model.layers.89.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00136-of-00191.safetensors | |
| model.layers.89.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00136-of-00191.safetensors | |
| model.layers.89.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00135-of-00191.safetensors | |
| model.layers.89.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00136-of-00191.safetensors | |
| model.layers.89.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00136-of-00191.safetensors | |
| model.layers.89.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00135-of-00191.safetensors | |
| model.layers.89.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00135-of-00191.safetensors | |
| model.layers.89.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00135-of-00191.safetensors | |
| model.layers.89.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00135-of-00191.safetensors | |
| model.layers.90.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00138-of-00191.safetensors | |
| model.layers.90.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00138-of-00191.safetensors | |
| model.layers.90.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00137-of-00191.safetensors | |
| model.layers.90.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00137-of-00191.safetensors | |
| model.layers.90.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00138-of-00191.safetensors | |
| model.layers.90.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00136-of-00191.safetensors | |
| model.layers.90.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00136-of-00191.safetensors | |
| model.layers.90.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00136-of-00191.safetensors | |
| model.layers.90.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00136-of-00191.safetensors | |
| model.layers.91.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00139-of-00191.safetensors | |
| model.layers.91.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00139-of-00191.safetensors | |
| model.layers.91.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00138-of-00191.safetensors | |
| model.layers.91.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00139-of-00191.safetensors | |
| model.layers.91.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00139-of-00191.safetensors | |
| model.layers.91.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00138-of-00191.safetensors | |
| model.layers.91.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00138-of-00191.safetensors | |
| model.layers.91.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00138-of-00191.safetensors | |
| model.layers.91.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00138-of-00191.safetensors | |
| model.layers.92.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00141-of-00191.safetensors | |
| model.layers.92.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00141-of-00191.safetensors | |
| model.layers.92.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00140-of-00191.safetensors | |
| model.layers.92.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00140-of-00191.safetensors | |
| model.layers.92.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00141-of-00191.safetensors | |
| model.layers.92.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00139-of-00191.safetensors | |
| model.layers.92.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00139-of-00191.safetensors | |
| model.layers.92.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00139-of-00191.safetensors | |
| model.layers.92.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00139-of-00191.safetensors | |
| model.layers.93.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00142-of-00191.safetensors | |
| model.layers.93.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00142-of-00191.safetensors | |
| model.layers.93.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00141-of-00191.safetensors | |
| model.layers.93.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00142-of-00191.safetensors | |
| model.layers.93.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00142-of-00191.safetensors | |
| model.layers.93.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00141-of-00191.safetensors | |
| model.layers.93.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00141-of-00191.safetensors | |
| model.layers.93.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00141-of-00191.safetensors | |
| model.layers.93.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00141-of-00191.safetensors | |
| model.layers.94.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00144-of-00191.safetensors | |
| model.layers.94.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00144-of-00191.safetensors | |
| model.layers.94.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00143-of-00191.safetensors | |
| model.layers.94.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00143-of-00191.safetensors | |
| model.layers.94.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00144-of-00191.safetensors | |
| model.layers.94.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00142-of-00191.safetensors | |
| model.layers.94.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00142-of-00191.safetensors | |
| model.layers.94.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00142-of-00191.safetensors | |
| model.layers.94.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00142-of-00191.safetensors | |
| model.layers.95.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00145-of-00191.safetensors | |
| model.layers.95.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00145-of-00191.safetensors | |
| model.layers.95.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00144-of-00191.safetensors | |
| model.layers.95.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00145-of-00191.safetensors | |
| model.layers.95.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00145-of-00191.safetensors | |
| model.layers.95.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00144-of-00191.safetensors | |
| model.layers.95.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00144-of-00191.safetensors | |
| model.layers.95.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00144-of-00191.safetensors | |
| model.layers.95.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00144-of-00191.safetensors | |
| model.layers.96.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00147-of-00191.safetensors | |
| model.layers.96.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00147-of-00191.safetensors | |
| model.layers.96.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00146-of-00191.safetensors | |
| model.layers.96.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00146-of-00191.safetensors | |
| model.layers.96.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00147-of-00191.safetensors | |
| model.layers.96.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00145-of-00191.safetensors | |
| model.layers.96.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00145-of-00191.safetensors | |
| model.layers.96.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00145-of-00191.safetensors | |
| model.layers.96.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00145-of-00191.safetensors | |
| model.layers.97.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00148-of-00191.safetensors | |
| model.layers.97.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00148-of-00191.safetensors | |
| model.layers.97.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00147-of-00191.safetensors | |
| model.layers.97.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00148-of-00191.safetensors | |
| model.layers.97.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00148-of-00191.safetensors | |
| model.layers.97.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00147-of-00191.safetensors | |
| model.layers.97.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00147-of-00191.safetensors | |
| model.layers.97.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00147-of-00191.safetensors | |
| model.layers.97.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00147-of-00191.safetensors | |
| model.layers.98.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00150-of-00191.safetensors | |
| model.layers.98.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00150-of-00191.safetensors | |
| model.layers.98.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00149-of-00191.safetensors | |
| model.layers.98.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00149-of-00191.safetensors | |
| model.layers.98.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00150-of-00191.safetensors | |
| model.layers.98.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00148-of-00191.safetensors | |
| model.layers.98.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00148-of-00191.safetensors | |
| model.layers.98.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00148-of-00191.safetensors | |
| model.layers.98.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00148-of-00191.safetensors | |
| model.layers.99.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00151-of-00191.safetensors | |
| model.layers.99.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00151-of-00191.safetensors | |
| model.layers.99.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00150-of-00191.safetensors | |
| model.layers.99.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00151-of-00191.safetensors | |
| model.layers.99.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00151-of-00191.safetensors | |
| model.layers.99.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00150-of-00191.safetensors | |
| model.layers.99.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00150-of-00191.safetensors | |
| model.layers.99.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00150-of-00191.safetensors | |
| model.layers.99.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00150-of-00191.safetensors | |
| model.layers.100.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00153-of-00191.safetensors | |
| model.layers.100.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00153-of-00191.safetensors | |
| model.layers.100.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00152-of-00191.safetensors | |
| model.layers.100.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00152-of-00191.safetensors | |
| model.layers.100.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00153-of-00191.safetensors | |
| model.layers.100.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00151-of-00191.safetensors | |
| model.layers.100.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00151-of-00191.safetensors | |
| model.layers.100.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00151-of-00191.safetensors | |
| model.layers.100.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00151-of-00191.safetensors | |
| model.layers.101.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00154-of-00191.safetensors | |
| model.layers.101.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00154-of-00191.safetensors | |
| model.layers.101.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00153-of-00191.safetensors | |
| model.layers.101.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00154-of-00191.safetensors | |
| model.layers.101.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00154-of-00191.safetensors | |
| model.layers.101.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00153-of-00191.safetensors | |
| model.layers.101.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00153-of-00191.safetensors | |
| model.layers.101.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00153-of-00191.safetensors | |
| model.layers.101.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00153-of-00191.safetensors | |
| model.layers.102.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00156-of-00191.safetensors | |
| model.layers.102.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00156-of-00191.safetensors | |
| model.layers.102.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00155-of-00191.safetensors | |
| model.layers.102.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00155-of-00191.safetensors | |
| model.layers.102.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00156-of-00191.safetensors | |
| model.layers.102.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00154-of-00191.safetensors | |
| model.layers.102.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00154-of-00191.safetensors | |
| model.layers.102.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00154-of-00191.safetensors | |
| model.layers.102.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00154-of-00191.safetensors | |
| model.layers.103.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00157-of-00191.safetensors | |
| model.layers.103.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00157-of-00191.safetensors | |
| model.layers.103.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00156-of-00191.safetensors | |
| model.layers.103.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00157-of-00191.safetensors | |
| model.layers.103.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00157-of-00191.safetensors | |
| model.layers.103.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00156-of-00191.safetensors | |
| model.layers.103.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00156-of-00191.safetensors | |
| model.layers.103.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00156-of-00191.safetensors | |
| model.layers.103.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00156-of-00191.safetensors | |
| model.layers.104.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00159-of-00191.safetensors | |
| model.layers.104.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00159-of-00191.safetensors | |
| model.layers.104.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00158-of-00191.safetensors | |
| model.layers.104.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00158-of-00191.safetensors | |
| model.layers.104.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00159-of-00191.safetensors | |
| model.layers.104.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00157-of-00191.safetensors | |
| model.layers.104.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00157-of-00191.safetensors | |
| model.layers.104.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00157-of-00191.safetensors | |
| model.layers.104.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00157-of-00191.safetensors | |
| model.layers.105.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00160-of-00191.safetensors | |
| model.layers.105.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00160-of-00191.safetensors | |
| model.layers.105.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00159-of-00191.safetensors | |
| model.layers.105.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00160-of-00191.safetensors | |
| model.layers.105.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00160-of-00191.safetensors | |
| model.layers.105.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00159-of-00191.safetensors | |
| model.layers.105.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00159-of-00191.safetensors | |
| model.layers.105.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00159-of-00191.safetensors | |
| model.layers.105.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00159-of-00191.safetensors | |
| model.layers.106.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00162-of-00191.safetensors | |
| model.layers.106.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00162-of-00191.safetensors | |
| model.layers.106.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00161-of-00191.safetensors | |
| model.layers.106.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00161-of-00191.safetensors | |
| model.layers.106.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00162-of-00191.safetensors | |
| model.layers.106.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00160-of-00191.safetensors | |
| model.layers.106.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00160-of-00191.safetensors | |
| model.layers.106.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00160-of-00191.safetensors | |
| model.layers.106.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00160-of-00191.safetensors | |
| model.layers.107.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00163-of-00191.safetensors | |
| model.layers.107.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00163-of-00191.safetensors | |
| model.layers.107.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00162-of-00191.safetensors | |
| model.layers.107.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00163-of-00191.safetensors | |
| model.layers.107.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00163-of-00191.safetensors | |
| model.layers.107.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00162-of-00191.safetensors | |
| model.layers.107.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00162-of-00191.safetensors | |
| model.layers.107.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00162-of-00191.safetensors | |
| model.layers.107.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00162-of-00191.safetensors | |
| model.layers.108.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00165-of-00191.safetensors | |
| model.layers.108.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00165-of-00191.safetensors | |
| model.layers.108.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00164-of-00191.safetensors | |
| model.layers.108.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00164-of-00191.safetensors | |
| model.layers.108.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00165-of-00191.safetensors | |
| model.layers.108.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00163-of-00191.safetensors | |
| model.layers.108.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00163-of-00191.safetensors | |
| model.layers.108.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00163-of-00191.safetensors | |
| model.layers.108.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00163-of-00191.safetensors | |
| model.layers.109.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00166-of-00191.safetensors | |
| model.layers.109.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00166-of-00191.safetensors | |
| model.layers.109.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00165-of-00191.safetensors | |
| model.layers.109.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00166-of-00191.safetensors | |
| model.layers.109.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00166-of-00191.safetensors | |
| model.layers.109.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00165-of-00191.safetensors | |
| model.layers.109.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00165-of-00191.safetensors | |
| model.layers.109.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00165-of-00191.safetensors | |
| model.layers.109.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00165-of-00191.safetensors | |
| model.layers.110.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00168-of-00191.safetensors | |
| model.layers.110.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00168-of-00191.safetensors | |
| model.layers.110.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00167-of-00191.safetensors | |
| model.layers.110.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00167-of-00191.safetensors | |
| model.layers.110.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00168-of-00191.safetensors | |
| model.layers.110.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00166-of-00191.safetensors | |
| model.layers.110.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00166-of-00191.safetensors | |
| model.layers.110.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00166-of-00191.safetensors | |
| model.layers.110.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00166-of-00191.safetensors | |
| model.layers.111.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00169-of-00191.safetensors | |
| model.layers.111.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00169-of-00191.safetensors | |
| model.layers.111.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00168-of-00191.safetensors | |
| model.layers.111.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00169-of-00191.safetensors | |
| model.layers.111.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00169-of-00191.safetensors | |
| model.layers.111.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00168-of-00191.safetensors | |
| model.layers.111.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00168-of-00191.safetensors | |
| model.layers.111.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00168-of-00191.safetensors | |
| model.layers.111.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00168-of-00191.safetensors | |
| model.layers.112.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00171-of-00191.safetensors | |
| model.layers.112.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00171-of-00191.safetensors | |
| model.layers.112.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00170-of-00191.safetensors | |
| model.layers.112.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00170-of-00191.safetensors | |
| model.layers.112.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00171-of-00191.safetensors | |
| model.layers.112.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00169-of-00191.safetensors | |
| model.layers.112.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00169-of-00191.safetensors | |
| model.layers.112.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00169-of-00191.safetensors | |
| model.layers.112.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00169-of-00191.safetensors | |
| model.layers.113.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00172-of-00191.safetensors | |
| model.layers.113.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00172-of-00191.safetensors | |
| model.layers.113.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00171-of-00191.safetensors | |
| model.layers.113.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00172-of-00191.safetensors | |
| model.layers.113.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00172-of-00191.safetensors | |
| model.layers.113.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00171-of-00191.safetensors | |
| model.layers.113.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00171-of-00191.safetensors | |
| model.layers.113.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00171-of-00191.safetensors | |
| model.layers.113.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00171-of-00191.safetensors | |
| model.layers.114.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00174-of-00191.safetensors | |
| model.layers.114.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00174-of-00191.safetensors | |
| model.layers.114.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00173-of-00191.safetensors | |
| model.layers.114.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00173-of-00191.safetensors | |
| model.layers.114.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00174-of-00191.safetensors | |
| model.layers.114.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00172-of-00191.safetensors | |
| model.layers.114.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00172-of-00191.safetensors | |
| model.layers.114.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00172-of-00191.safetensors | |
| model.layers.114.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00172-of-00191.safetensors | |
| model.layers.115.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00175-of-00191.safetensors | |
| model.layers.115.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00175-of-00191.safetensors | |
| model.layers.115.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00174-of-00191.safetensors | |
| model.layers.115.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00175-of-00191.safetensors | |
| model.layers.115.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00175-of-00191.safetensors | |
| model.layers.115.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00174-of-00191.safetensors | |
| model.layers.115.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00174-of-00191.safetensors | |
| model.layers.115.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00174-of-00191.safetensors | |
| model.layers.115.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00174-of-00191.safetensors | |
| model.layers.116.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00177-of-00191.safetensors | |
| model.layers.116.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00177-of-00191.safetensors | |
| model.layers.116.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00176-of-00191.safetensors | |
| model.layers.116.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00176-of-00191.safetensors | |
| model.layers.116.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00177-of-00191.safetensors | |
| model.layers.116.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00175-of-00191.safetensors | |
| model.layers.116.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00175-of-00191.safetensors | |
| model.layers.116.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00175-of-00191.safetensors | |
| model.layers.116.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00175-of-00191.safetensors | |
| model.layers.117.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00178-of-00191.safetensors | |
| model.layers.117.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00178-of-00191.safetensors | |
| model.layers.117.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00177-of-00191.safetensors | |
| model.layers.117.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00178-of-00191.safetensors | |
| model.layers.117.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00178-of-00191.safetensors | |
| model.layers.117.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00177-of-00191.safetensors | |
| model.layers.117.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00177-of-00191.safetensors | |
| model.layers.117.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00177-of-00191.safetensors | |
| model.layers.117.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00177-of-00191.safetensors | |
| model.layers.118.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00180-of-00191.safetensors | |
| model.layers.118.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00180-of-00191.safetensors | |
| model.layers.118.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00179-of-00191.safetensors | |
| model.layers.118.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00179-of-00191.safetensors | |
| model.layers.118.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00180-of-00191.safetensors | |
| model.layers.118.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00178-of-00191.safetensors | |
| model.layers.118.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00178-of-00191.safetensors | |
| model.layers.118.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00178-of-00191.safetensors | |
| model.layers.118.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00178-of-00191.safetensors | |
| model.layers.119.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00181-of-00191.safetensors | |
| model.layers.119.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00181-of-00191.safetensors | |
| model.layers.119.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00180-of-00191.safetensors | |
| model.layers.119.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00181-of-00191.safetensors | |
| model.layers.119.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00181-of-00191.safetensors | |
| model.layers.119.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00180-of-00191.safetensors | |
| model.layers.119.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00180-of-00191.safetensors | |
| model.layers.119.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00180-of-00191.safetensors | |
| model.layers.119.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00180-of-00191.safetensors | |
| model.layers.120.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00183-of-00191.safetensors | |
| model.layers.120.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00183-of-00191.safetensors | |
| model.layers.120.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00182-of-00191.safetensors | |
| model.layers.120.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00182-of-00191.safetensors | |
| model.layers.120.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00183-of-00191.safetensors | |
| model.layers.120.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00181-of-00191.safetensors | |
| model.layers.120.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00181-of-00191.safetensors | |
| model.layers.120.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00181-of-00191.safetensors | |
| model.layers.120.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00181-of-00191.safetensors | |
| model.layers.121.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00184-of-00191.safetensors | |
| model.layers.121.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00184-of-00191.safetensors | |
| model.layers.121.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00183-of-00191.safetensors | |
| model.layers.121.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00184-of-00191.safetensors | |
| model.layers.121.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00184-of-00191.safetensors | |
| model.layers.121.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00183-of-00191.safetensors | |
| model.layers.121.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00183-of-00191.safetensors | |
| model.layers.121.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00183-of-00191.safetensors | |
| model.layers.121.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00183-of-00191.safetensors | |
| model.layers.122.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00186-of-00191.safetensors | |
| model.layers.122.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00186-of-00191.safetensors | |
| model.layers.122.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00185-of-00191.safetensors | |
| model.layers.122.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00185-of-00191.safetensors | |
| model.layers.122.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00186-of-00191.safetensors | |
| model.layers.122.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00184-of-00191.safetensors | |
| model.layers.122.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00184-of-00191.safetensors | |
| model.layers.122.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00184-of-00191.safetensors | |
| model.layers.122.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00184-of-00191.safetensors | |
| model.layers.123.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00187-of-00191.safetensors | |
| model.layers.123.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00187-of-00191.safetensors | |
| model.layers.123.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00186-of-00191.safetensors | |
| model.layers.123.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00187-of-00191.safetensors | |
| model.layers.123.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00187-of-00191.safetensors | |
| model.layers.123.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00186-of-00191.safetensors | |
| model.layers.123.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00186-of-00191.safetensors | |
| model.layers.123.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00186-of-00191.safetensors | |
| model.layers.123.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00186-of-00191.safetensors | |
| model.layers.124.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00189-of-00191.safetensors | |
| model.layers.124.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00189-of-00191.safetensors | |
| model.layers.124.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00188-of-00191.safetensors | |
| model.layers.124.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00188-of-00191.safetensors | |
| model.layers.124.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00189-of-00191.safetensors | |
| model.layers.124.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00187-of-00191.safetensors | |
| model.layers.124.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00187-of-00191.safetensors | |
| model.layers.124.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00187-of-00191.safetensors | |
| model.layers.124.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00187-of-00191.safetensors | |
| model.layers.125.input_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00190-of-00191.safetensors | |
| model.layers.125.mlp.down_proj.weight | 872_415_232 | torch.bfloat16 | (16384, 53248) | model-00190-of-00191.safetensors | |
| model.layers.125.mlp.gate_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00189-of-00191.safetensors | |
| model.layers.125.mlp.up_proj.weight | 872_415_232 | torch.bfloat16 | (53248, 16384) | model-00190-of-00191.safetensors | |
| model.layers.125.post_attention_layernorm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00190-of-00191.safetensors | |
| model.layers.125.self_attn.k_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00189-of-00191.safetensors | |
| model.layers.125.self_attn.o_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00189-of-00191.safetensors | |
| model.layers.125.self_attn.q_proj.weight | 268_435_456 | torch.bfloat16 | (16384, 16384) | model-00189-of-00191.safetensors | |
| model.layers.125.self_attn.v_proj.weight | 16_777_216 | torch.bfloat16 | (1024, 16384) | model-00189-of-00191.safetensors | |
| model.norm.weight | 16_384 | torch.bfloat16 | (16384,) | model-00190-of-00191.safetensors |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment