ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

use pre-commit

Browse Source 
Former-commit-id: 7cfede95df22a9ff236788f04159b6b16b8d04bb
This commit is contained in:
hiyouga
2024-10-29 09:07:46 +00:00
parent 8f5921692e
commit 248d5daaff
66 changed files with 1028 additions and 1044 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
scripts/llamafy_qwen.py
View File

@@ -1,4 +1,3 @@
# coding=utf-8
# Copyright 2024 the LlamaFactory team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
@@ -86,7 +85,7 @@ def save_weight(input_dir: str, output_dir: str, shard_size: str, save_safetenso
elif "lm_head" in key:
llama2_state_dict[key] = value
else:
raise KeyError("Unable to process key {}".format(key))
raise KeyError(f"Unable to process key {key}")
weights_name = SAFE_WEIGHTS_NAME if save_safetensors else WEIGHTS_NAME
shards, index = shard_checkpoint(llama2_state_dict, max_shard_size=shard_size, weights_name=weights_name)
@@ -98,18 +97,18 @@ def save_weight(input_dir: str, output_dir: str, shard_size: str, save_safetenso
torch.save(shard, os.path.join(output_dir, shard_file))
if index is None:
print("Model weights saved in {}".format(os.path.join(output_dir, weights_name)))
print(f"Model weights saved in {os.path.join(output_dir, weights_name)}")
else:
index_name = SAFE_WEIGHTS_INDEX_NAME if save_safetensors else WEIGHTS_INDEX_NAME
with open(os.path.join(output_dir, index_name), "w", encoding="utf-8") as f:
json.dump(index, f, indent=2, sort_keys=True)
print("Model weights saved in {}".format(output_dir))
print(f"Model weights saved in {output_dir}")
return str(torch_dtype).replace("torch.", "")
def save_config(input_dir: str, output_dir: str, torch_dtype: str):
with open(os.path.join(input_dir, CONFIG_NAME), "r", encoding="utf-8") as f:
with open(os.path.join(input_dir, CONFIG_NAME), encoding="utf-8") as f:
qwen_config_dict: Dict[str, Any] = json.load(f)
llama2_config_dict: Dict[str, Any] = OrderedDict()
@@ -135,7 +134,7 @@ def save_config(input_dir: str, output_dir: str, torch_dtype: str):
with open(os.path.join(output_dir, CONFIG_NAME), "w", encoding="utf-8") as f:
json.dump(llama2_config_dict, f, indent=2)
print("Model config saved in {}".format(os.path.join(output_dir, CONFIG_NAME)))
print(f"Model config saved in {os.path.join(output_dir, CONFIG_NAME)}")
def llamafy_qwen(