Guideline for generating correct lit_model.pth

[mkeya013]

Dear Author, is it possible to provide correct lit_model.pth file? Or a guideline to generate correct lit_model.pth file would be a great help.

Thank you.

[LinghaoChan]

@mkeya013 Thanks for your question.

1. git clone the `lit-gpt' and go into the corresponding dictionary.

git clone https://github.com/Lightning-AI/litgpt.git
cd litgpt
git checkout d78730a0694bff6c9f1ce285a6e8b471c1321cf5
cd ./litgpt/scripts

To see all the available checkpoints for Vicuna, run:

python scripts/download.py | grep vicuna

which will print

lmsys/vicuna-7b-v1.3
lmsys/vicuna-13b-v1.3
lmsys/vicuna-33b-v1.3
lmsys/vicuna-7b-v1.5
lmsys/vicuna-7b-v1.5-16k
lmsys/vicuna-13b-v1.5
lmsys/vicuna-13b-v1.5-16k

2. Download the model.

In order to use a specific Vicuna checkpoint, for instance vicuna-7b-v1.5, download the weights and convert the checkpoint to the lit-gpt format:

pip install huggingface_hub

python scripts/download.py --repo_id lmsys/vicuna-7b-v1.5

python scripts/convert_hf_checkpoint.py --checkpoint_dir checkpoints/lmsys/vicuna-7b-v1.5

By default, the convert_hf_checkpoint step will use the data type of the HF checkpoint's parameters. In cases where RAM
or disk size is constrained, it might be useful to pass --dtype bfloat16 to convert all parameters into this smaller precision before continuing.

You're done! To execute the model just run:

pip install sentencepiece

python chat/base.py --checkpoint_dir checkpoints/lmsys/vicuna-7b-v1.5

---

This is the vicuna version I used. You can also follow the latest official guideline and revise it to vicuna-7b-1.5.

[mkeya013]

It worked. Thank you.

[CMY-CTO]

Dear Author,

For Step1: git clone the `lit-gpt' and go into the corresponding dictionary.

It's not workin

Is it possible to provide correct repository？

Thank you.

[LinghaoChan]

@CMY-CTO sry for this. plz revise as

git clone https://github.com/Lightning-AI/litgpt.git
cd litgpt
git checkout d78730a0694bff6c9f1ce285a6e8b471c1321cf5

[LinghaoChan]

@LinghaoChan 你好，我按照这个流程操作的时候报错 from litgpt.scripts.convert_hf_checkpoint import convert_hf_checkpoint ModuleNotFoundError: No module named 'litgpt' 请问该怎么修改啊，从huggingface或是modelscope的模型库中好像都有没有lit_model.pth这个模型

@ransheng11 需要按照README所说下载vicuna-1.5-7B的model哦～～～

[LinghaoChan]

@LinghaoChan 你好，我按照这个流程操作的时候报错 from litgpt.scripts.convert_hf_checkpoint import convert_hf_checkpoint ModuleNotFoundError: No module named 'litgpt' 请问该怎么修改啊，从huggingface或是modelscope的模型库中好像都有没有lit_model.pth这个模型

@ransheng11 需要按照README所说下载vicuna-1.5-7B的model哦～～～

你好，谢谢你的及时回答，我的问题可能有点白痴了，我现在仍然没有运行成功 1.python scripts/download.py --repo_id lmsys/vicuna-7b-v1.5 2.python scripts/convert_hf_checkpoint.py --checkpoint_dir checkpoints/lmsys/vicuna-7b-v1.5 在运行第一个命令的时候报如下错误，我用其他方式下载了模型如图 raise ConnectionError(err, request=request) requests.exceptions.ConnectionError: (ProtocolError('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer')), '(Request ID: c301ebb9-2ae9-44b6-8071-74d95a5a9ad4)') 运行第二个命令的时候报如下错误，但我在huggingface和modelscope都没有看到有这个文件 FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints/lmsys/vicuna-7b-v1.5/model_config.yaml'

Please refer to the guidance provided by lig-gpt.

[ransheng11]

@LinghaoChan Thanks. I think I have followed the guidelines of litgpt. But it's okay. I have downloaded the model from hf. But now I get an out-of-memory error when running cli. I have 24GB of memory. Does motionllm support multiple cards? And does it support fine-tuning with custom datasets?