Skip to content

Instantly share code, notes, and snippets.

@siddhant3s

siddhant3s/gist:021224c1ef21e5c48bf54db1eefdc1af

Created December 16, 2023 02:48
Show Gist options
  • Save siddhant3s/021224c1ef21e5c48bf54db1eefdc1af to your computer and use it in GitHub Desktop.
Save siddhant3s/021224c1ef21e5c48bf54db1eefdc1af to your computer and use it in GitHub Desktop.
Download ZIP
Raw
gistfile1.txt
Error: could not connect to ollama app, is it running?
ssanyam-macbookpro:~ ssanyam$ ollama serve
2023/12/15 18:44:35 images.go:779: total blobs: 15
2023/12/15 18:44:35 images.go:786: total unused blobs removed: 0
2023/12/15 18:44:35 routes.go:777: Listening on 127.0.0.1:11434 (version 0.1.11)
[GIN] 2023/12/15 - 18:44:50 | 200 | 166.791µs | 127.0.0.1 | HEAD "/"
[GIN] 2023/12/15 - 18:44:50 | 200 | 1.642208ms | 127.0.0.1 | POST "/api/show"
2023/12/15 18:44:50 llama.go:420: starting llama runner
2023/12/15 18:44:50 llama.go:478: waiting for llama runner to start responding
{"timestamp":1702694691,"level":"INFO","function":"main","line":1324,"message":"build info","build":219,"commit":"9e70cc0"}
{"timestamp":1702694691,"level":"INFO","function":"main","line":1330,"message":"system info","n_threads":8,"n_threads_batch":-1,"total_threads":10,"system_info":"AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | "}
llama_model_loader: loaded meta data with 19 key-value pairs and 363 tensors from /Users/ssanyam/.ollama/models/blobs/sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2 (version GGUF V2 (latest))
llama_model_loader: - tensor 0: token_embd.weight q4_0 [ 5120, 32000, 1, 1 ]
llama_model_loader: - tensor 1: blk.0.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 2: blk.0.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 3: blk.0.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 4: blk.0.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 5: blk.0.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 6: blk.0.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 7: blk.0.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 8: blk.0.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 9: blk.0.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 10: blk.1.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 11: blk.1.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 12: blk.1.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 13: blk.1.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 14: blk.1.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 15: blk.1.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 16: blk.1.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 17: blk.1.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 18: blk.1.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 19: blk.10.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 20: blk.10.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 21: blk.10.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 22: blk.10.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 23: blk.10.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 24: blk.10.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 25: blk.10.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 26: blk.10.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 27: blk.10.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 28: blk.11.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 29: blk.11.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 30: blk.11.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 31: blk.11.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 32: blk.11.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 33: blk.11.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 34: blk.11.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 35: blk.11.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 36: blk.11.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 37: blk.12.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 38: blk.12.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 39: blk.12.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 40: blk.12.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 41: blk.12.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 42: blk.12.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 43: blk.12.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 44: blk.12.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 45: blk.12.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 46: blk.13.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 47: blk.13.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 48: blk.13.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 49: blk.13.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 50: blk.13.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 51: blk.13.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 52: blk.13.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 53: blk.13.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 54: blk.13.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 55: blk.14.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 56: blk.14.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 57: blk.14.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 58: blk.14.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 59: blk.14.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 60: blk.14.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 61: blk.14.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 62: blk.14.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 63: blk.14.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 64: blk.15.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 65: blk.15.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 66: blk.2.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 67: blk.2.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 68: blk.2.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 69: blk.2.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 70: blk.2.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 71: blk.2.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 72: blk.2.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 73: blk.2.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 74: blk.2.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 75: blk.3.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 76: blk.3.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 77: blk.3.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 78: blk.3.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 79: blk.3.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 80: blk.3.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 81: blk.3.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 82: blk.3.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 83: blk.3.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 84: blk.4.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 85: blk.4.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 86: blk.4.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 87: blk.4.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 88: blk.4.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 89: blk.4.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 90: blk.4.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 91: blk.4.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 92: blk.4.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 93: blk.5.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 94: blk.5.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 95: blk.5.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 96: blk.5.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 97: blk.5.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 98: blk.5.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 99: blk.5.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 100: blk.5.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 101: blk.5.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 102: blk.6.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 103: blk.6.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 104: blk.6.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 105: blk.6.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 106: blk.6.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 107: blk.6.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 108: blk.6.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 109: blk.6.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 110: blk.6.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 111: blk.7.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 112: blk.7.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 113: blk.7.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 114: blk.7.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 115: blk.7.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 116: blk.7.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 117: blk.7.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 118: blk.7.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 119: blk.7.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 120: blk.8.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 121: blk.8.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 122: blk.8.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 123: blk.8.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 124: blk.8.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 125: blk.8.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 126: blk.8.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 127: blk.8.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 128: blk.8.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 129: blk.9.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 130: blk.9.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 131: blk.9.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 132: blk.9.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 133: blk.9.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 134: blk.9.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 135: blk.9.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 136: blk.9.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 137: blk.9.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 138: blk.15.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 139: blk.15.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 140: blk.15.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 141: blk.15.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 142: blk.15.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 143: blk.15.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 144: blk.15.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 145: blk.16.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 146: blk.16.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 147: blk.16.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 148: blk.16.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 149: blk.16.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 150: blk.16.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 151: blk.16.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 152: blk.16.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 153: blk.16.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 154: blk.17.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 155: blk.17.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 156: blk.17.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 157: blk.17.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 158: blk.17.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 159: blk.17.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 160: blk.17.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 161: blk.17.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 162: blk.17.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 163: blk.18.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 164: blk.18.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 165: blk.18.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 166: blk.18.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 167: blk.18.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 168: blk.18.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 169: blk.18.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 170: blk.18.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 171: blk.18.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 172: blk.19.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 173: blk.19.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 174: blk.19.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 175: blk.19.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 176: blk.19.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 177: blk.19.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 178: blk.19.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 179: blk.19.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 180: blk.19.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 181: blk.20.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 182: blk.20.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 183: blk.20.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 184: blk.20.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 185: blk.20.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 186: blk.20.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 187: blk.20.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 188: blk.20.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 189: blk.20.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 190: blk.21.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 191: blk.21.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 192: blk.21.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 193: blk.21.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 194: blk.21.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 195: blk.21.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 196: blk.21.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 197: blk.21.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 198: blk.21.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 199: blk.22.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 200: blk.22.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 201: blk.22.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 202: blk.22.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 203: blk.22.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 204: blk.22.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 205: blk.22.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 206: blk.22.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 207: blk.22.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 208: blk.23.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 209: blk.23.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 210: blk.23.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 211: blk.23.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 212: blk.23.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 213: blk.23.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 214: blk.23.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 215: blk.23.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 216: blk.23.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 217: blk.24.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 218: blk.24.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 219: blk.24.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 220: blk.24.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 221: blk.24.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 222: blk.24.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 223: blk.24.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 224: blk.24.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 225: blk.24.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 226: blk.25.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 227: blk.25.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 228: blk.25.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 229: blk.25.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 230: blk.25.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 231: blk.25.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 232: blk.25.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 233: blk.25.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 234: blk.25.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 235: blk.26.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 236: blk.26.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 237: blk.26.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 238: blk.26.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 239: blk.26.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 240: blk.26.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 241: blk.26.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 242: blk.26.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 243: blk.26.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 244: blk.27.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 245: blk.27.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 246: blk.27.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 247: blk.27.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 248: blk.27.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 249: blk.27.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 250: blk.27.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 251: blk.27.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 252: blk.27.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 253: blk.28.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 254: blk.28.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 255: blk.28.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 256: blk.28.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 257: blk.28.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 258: blk.28.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 259: blk.28.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 260: blk.28.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 261: blk.28.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 262: blk.29.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 263: blk.29.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 264: blk.29.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 265: blk.29.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 266: blk.29.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 267: blk.29.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 268: blk.29.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 269: blk.29.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 270: blk.29.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 271: blk.30.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 272: blk.30.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 273: blk.30.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 274: blk.30.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 275: blk.30.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 276: blk.30.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 277: output.weight q6_K [ 5120, 32000, 1, 1 ]
llama_model_loader: - tensor 278: blk.30.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 279: blk.30.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 280: blk.30.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 281: blk.31.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 282: blk.31.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 283: blk.31.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 284: blk.31.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 285: blk.31.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 286: blk.31.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 287: blk.31.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 288: blk.31.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 289: blk.31.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 290: blk.32.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 291: blk.32.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 292: blk.32.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 293: blk.32.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 294: blk.32.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 295: blk.32.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 296: blk.32.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 297: blk.32.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 298: blk.32.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 299: blk.33.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 300: blk.33.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 301: blk.33.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 302: blk.33.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 303: blk.33.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 304: blk.33.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 305: blk.33.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 306: blk.33.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 307: blk.33.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 308: blk.34.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 309: blk.34.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 310: blk.34.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 311: blk.34.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 312: blk.34.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 313: blk.34.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 314: blk.34.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 315: blk.34.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 316: blk.34.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 317: blk.35.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 318: blk.35.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 319: blk.35.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 320: blk.35.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 321: blk.35.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 322: blk.35.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 323: blk.35.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 324: blk.35.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 325: blk.35.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 326: blk.36.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 327: blk.36.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 328: blk.36.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 329: blk.36.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 330: blk.36.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 331: blk.36.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 332: blk.36.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 333: blk.36.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 334: blk.36.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 335: blk.37.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 336: blk.37.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 337: blk.37.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 338: blk.37.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 339: blk.37.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 340: blk.37.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 341: blk.37.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 342: blk.37.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 343: blk.37.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 344: blk.38.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 345: blk.38.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 346: blk.38.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 347: blk.38.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 348: blk.38.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 349: blk.38.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 350: blk.38.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 351: blk.38.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 352: blk.38.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 353: blk.39.attn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 354: blk.39.ffn_down.weight q4_0 [ 13824, 5120, 1, 1 ]
llama_model_loader: - tensor 355: blk.39.ffn_gate.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 356: blk.39.ffn_up.weight q4_0 [ 5120, 13824, 1, 1 ]
llama_model_loader: - tensor 357: blk.39.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - tensor 358: blk.39.attn_k.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 359: blk.39.attn_output.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 360: blk.39.attn_q.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 361: blk.39.attn_v.weight q4_0 [ 5120, 5120, 1, 1 ]
llama_model_loader: - tensor 362: output_norm.weight f32 [ 5120, 1, 1, 1 ]
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: general.name str
llama_model_loader: - kv 2: llama.context_length u32
llama_model_loader: - kv 3: llama.embedding_length u32
llama_model_loader: - kv 4: llama.block_count u32
llama_model_loader: - kv 5: llama.feed_forward_length u32
llama_model_loader: - kv 6: llama.rope.dimension_count u32
llama_model_loader: - kv 7: llama.attention.head_count u32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv 10: general.file_type u32
llama_model_loader: - kv 11: tokenizer.ggml.model str
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr
llama_model_loader: - kv 13: tokenizer.ggml.scores arr
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32
llama_model_loader: - kv 18: general.quantization_version u32
llama_model_loader: - type f32: 81 tensors
llama_model_loader: - type q4_0: 281 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_vocab: special tokens definition check successful ( 259/32000 ).
llm_load_print_meta: format = GGUF V2 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 4096
llm_load_print_meta: n_embd = 5120
llm_load_print_meta: n_head = 40
llm_load_print_meta: n_head_kv = 40
llm_load_print_meta: n_layer = 40
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff = 13824
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: model type = 13B
llm_load_print_meta: model ftype = mostly Q4_0
llm_load_print_meta: model params = 13.02 B
llm_load_print_meta: model size = 6.86 GiB (4.53 BPW)
llm_load_print_meta: general.name = LLaMA v2
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.12 MB
llm_load_tensors: mem required = 7024.02 MB
...................................................................................................
llama_new_context_with_model: n_ctx = 4096
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: kv self size = 3200.00 MB
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1 Pro
ggml_metal_init: picking default device: Apple M1 Pro
ggml_metal_init: default.metallib not found, loading from source
ggml_metal_init: loading '/var/folders/k9/r42kbc9x0lz5_3t72kz9gmrc011sq3/T/ollama1700140781/llama.cpp/gguf/build/metal/bin/ggml-metal.metal'
ggml_metal_init: loaded kernel_add 0x101604420 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_add_row 0x14f7078c0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul 0x101605270 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_row 0x101605660 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_scale 0x14f708600 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_scale_4 0x14f60a280 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_silu 0x14f60aa80 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_relu 0x14f60b230 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_gelu 0x14f708dc0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_soft_max 0x14f708ff0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_soft_max_4 0x14f7098b0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_diag_mask_inf 0x101606230 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_diag_mask_inf_8 0x1016068d0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_f32 0x101606df0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_f16 0x101607310 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q4_0 0x101607830 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q4_1 0x101607d50 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q5_0 0x14f709c00 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q5_1 0x101607f80 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q8_0 0x14f70a100 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q2_K 0x1016087e0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q3_K 0x14f70a610 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q4_K 0x1011042a0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q5_K 0x14f70b180 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q6_K 0x101608ce0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_rms_norm 0x14f70b520 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_norm 0x1016091f0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_f32_f32 0x14f70bd70 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_f16_f32 0x101609760 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_f16_f32_1row 0x14f60b460 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_f16_f32_l4 0x10160a080 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q4_0_f32 0x10160a8e0 | th_max = 896 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q4_1_f32 0x10160ab10 | th_max = 896 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q5_0_f32 0x10160afc0 | th_max = 576 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q5_1_f32 0x14f70c160 | th_max = 576 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q8_0_f32 0x14f70ca30 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q2_K_f32 0x10160b470 | th_max = 640 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q3_K_f32 0x10160bd90 | th_max = 576 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q4_K_f32 0x14f70cc60 | th_max = 576 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q5_K_f32 0x10160bfc0 | th_max = 576 | th_width = 32
ggml_metal_init: loaded kernel_mul_mv_q6_K_f32 0x10160c8e0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_f32_f32 0x10160ce00 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_f16_f32 0x14f70d230 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q4_0_f32 0x10160d030 | th_max = 704 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q4_1_f32 0x10160d950 | th_max = 704 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q5_0_f32 0x1011047b0 | th_max = 704 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q5_1_f32 0x14f70d740 | th_max = 704 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q8_0_f32 0x10160db80 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q2_K_f32 0x14f70ae60 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q3_K_f32 0x10160e460 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q4_K_f32 0x10160e970 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q5_K_f32 0x14f70de10 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q6_K_f32 0x14f70e430 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_rope_f32 0x10160ee80 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_rope_f16 0x10160f700 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_alibi_f32 0x14f70e940 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_cpy_f32_f16 0x10160f930 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_cpy_f32_f32 0x101610240 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_cpy_f16_f16 0x101610760 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_concat 0x101610c80 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_sqr 0x1011053c0 | th_max = 1024 | th_width = 32
ggml_metal_init: GPU name: Apple M1 Pro
ggml_metal_init: GPU family: MTLGPUFamilyApple7 (1007)
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 10922.67 MB
ggml_metal_init: maxTransferRate = built-in GPU
llama_new_context_with_model: compute buffer total size = 364.13 MB
llama_new_context_with_model: max tensor size = 128.17 MB
ggml_metal_add_buffer: allocated 'data ' buffer, size = 7024.61 MB, ( 7025.23 / 10922.67)
ggml_metal_add_buffer: allocated 'kv ' buffer, size = 3200.02 MB, (10225.25 / 10922.67)
ggml_metal_add_buffer: allocated 'alloc ' buffer, size = 358.02 MB, (10583.27 / 10922.67)
llama server listening at http://127.0.0.1:52056
{"timestamp":1702694706,"level":"INFO","function":"main","line":1749,"message":"HTTP server listening","hostname":"127.0.0.1","port":52056}
{"timestamp":1702694706,"level":"INFO","function":"log_server_request","line":1240,"message":"request","remote_addr":"127.0.0.1","remote_port":49939,"status":200,"method":"HEAD","path":"/","params":{}}
2023/12/15 18:45:06 llama.go:492: llama runner started in 15.613460 seconds
[GIN] 2023/12/15 - 18:45:06 | 200 | 15.721239834s | 127.0.0.1 | POST "/api/generate"
{"timestamp":1702694720,"level":"INFO","function":"log_server_request","line":1240,"message":"request","remote_addr":"127.0.0.1","remote_port":49956,"status":200,"method":"HEAD","path":"/","params":{}}
[GIN] 2023/12/15 - 18:45:34 | 200 | 14.0118785s | 127.0.0.1 | POST "/api/generate"
llama_print_timings: load time = 15114.93 ms
llama_print_timings: sample time = 3.33 ms / 25 runs ( 0.13 ms per token, 7498.50 tokens per second)
llama_print_timings: prompt eval time = 2982.78 ms / 195 tokens ( 15.30 ms per token, 65.38 tokens per second)
llama_print_timings: eval time = 11241.31 ms / 24 runs ( 468.39 ms per token, 2.13 tokens per second)
llama_print_timings: total time = 14256.40 ms
{"timestamp":1702694734,"level":"INFO","function":"log_server_request","line":1240,"message":"request","remote_addr":"127.0.0.1","remote_port":49956,"status":200,"method":"POST","path":"/completion","params":{}}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment