xagentllama-34b-preview 使用transformer加载报错： model = AutoModelForCausalLM.from_pretrained( File "/data/envs_qwen_xgentllama_service/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py", line 566, in from_pretrained return model_class.from_pretrained( File "/envs_qwen_xgentllama_service/lib/python3.9/site-packages/transformers/modeling_utils.py", line 3206, in from_pretrained raise EnvironmentError( OSError: Error no file named pytorch_model.bin, tf_model.h5,

Issue Description / 问题描述

Please provide a detailed description of the error or issue you encountered. / 请详细描述您遇到的错误或问题。
xagentllama-34b-preview , 模型包 不包含pytorch_model.bin.index.json， 使用transformer加载失败：
model = AutoModelForCausalLM.from_pretrained( File "/data/envs_qwen_xgentllama_service/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py", line 566, in from_pretrained return model_class.from_pretrained( File "/envs_qwen_xgentllama_service/lib/python3.9/site-packages/transformers/modeling_utils.py", line 3206, in from_pretrained raise EnvironmentError( OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in

模型包：共154G
config.json pytorch_model-00012-of-00017.bin
generation_config.json pytorch_model-00013-of-00017.bin
pytorch_model-00001-of-00017.bin pytorch_model-00014-of-00017.bin
pytorch_model-00002-of-00017.bin pytorch_model-00015-of-00017.bin
pytorch_model-00003-of-00017.bin pytorch_model-00016-of-00017.bin
pytorch_model-00004-of-00017.bin pytorch_model-00017-of-00017.bin
pytorch_model-00005-of-00017.bin
pytorch_model-00006-of-00017.bin README.md
pytorch_model-00007-of-00017.bin special_tokens_map.json
pytorch_model-00008-of-00017.bin tokenizer_config.json
pytorch_model-00009-of-00017.bin tokenizer.json
pytorch_model-00010-of-00017.bin tokenizer.model
pytorch_model-00011-of-00017.bin

Steps to Reproduce / 复现步骤

Please provide the specific steps to reproduce the error. / 请提供复现错误的具体步骤。

代码：
import os
from transformers import AutoModelForCausalLM
import torch
from transformers import BitsAndBytesConfig
model_name_or_path = "/data1/xagentllama-34b-preview/"
tokenizer_name_or_path = model_name_or_path
model = AutoModelForCausalLM.from_pretrained(
model_name_or_path,
local_files_only=True,# trust_remote_code=True,
quantization_config = BitsAndBytesConfig(
# 量化数据类型设置
bnb_4bit_quant_type="nf4",
# 量化数据的数据格式
bnb_4bit_compute_dtype=torch.bfloat16
),
device_map='auto',
torch_dtype=torch.bfloat16,
)

output = "/data1/lilei107/xagentllama-34b-preview-4bit"
if not os.path.exists(output):
os.mkdir(output)

model.save_pretrained(output)
print("done")
exit(0)

执行报错： OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in

发现模型包和huggingface 中都没有类似于 pytorch_model.bin.index.json 这个模型参数文件， 是否可以提供下这个文件?

谢谢！

Expected Behavior / 预期行为

Describe the behavior you expected to see. / 请描述您期望的正确行为。

Environment / 环境信息

• Operating System / 操作系统：
• Python Version / Python 版本：
• Other Relevant Information / 其他相关信息：

Error Screenshots or Logs / 错误截图或日志

If possible, please provide relevant screenshots or logs of the error. / 如果可能，请提供相关的错误截图或日志文件。

Additional Notes / 其他备注

If you have any additional information or notes, please add them here. / 如果有其他补充信息，请在此处添加。

Start with the reported AutoModelForCausalLM.from_pretrained call and inspect the local xagentllama-34b-preview directory, especially config.json and the 17 pytorch_model shard files. Compare the directory contents with the files Transformers expects for loading a sharded checkpoint. Done means the supplied model package loads locally and the reported OSError no longer occurs.