sekstini sekstini
sekstini
/ dump_4bit_llama_2_7b_linear.py
Last active
July 31, 2023 22:01
This file contains hidden or 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
| # %% | |
| import torch | |
| from transformers import AutoModelForCausalLM, BitsAndBytesConfig | |
| # %% | |
| import bitsandbytes as bnb # type: ignore | |
| def dump_4bit_weight(m: bnb.nn.modules.Linear4bit, path: str): | |
| assert isinstance(m, bnb.nn.modules.Linear4bit), "Only Linear4bit is supported" | |
| obj = { |
sekstini
/ weightcomp.ipynb
Created
July 19, 2023 21:58
LLaMA-2 7b weight comparison between original (bf16) and huggingface (fp16)
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
NewerOlder