Llama chat: 基于llama的聊天模式

通过prompt设计让模型能够用于对话（见example.py）

环境配置方法和和原readme相同，使用时运行

python example.py --ckpt_dir xxxx/13B --tokenizer_path xxxx/tokenizer.model

等待加载完后出现>字符即可开始输入。

13B模型在单张3090上占用16G显存

以下是原readme

This is a fork of the LLaMA code that runs LLaMA-13B comfortably within 24 GiB of RAM. It relies almost entirely on the bitsandbytes and LLM.int8() work of Tim Dettmers. I've tested it on an RTX 4090, and it reportedly works on the 3090. It might also theoretically allow us to run LLaMA-65B on an 80GB A100, but I haven't tried this.

The code contains the following changes:

• Removes parallelism constructs
• Quantizes weights on the host machine
• Loads weights incrementally to avoid severe memory problems
• Added dependencies on bitsandbytes, tqdm.
• Repetition penalty settings (--repetition_penalty, default 1.15)

On my Ubuntu machine with 64 GB of RAM and an RTX 4090, it takes about 25 seconds to load in the floats and quantize the model. Users should be ready to expand their swapfiles if they don't have enough RAM. Llamanon has also produced a slightly uncouth user's guide for using this repo, which I won't reproduce here but seems generally trustworthy. You will likely need to build bitsandbytes from source.

If you have interesting ideas for further development, I can be reached at https://twitter.com/ecjwg.

python example.py --ckpt_dir [TARGET_DIR]/13B --tokenizer_path [TARGET_DIR]/tokenizer.model --max_batch_size=1

This repository is intended as a minimal, hackable and readable example to load LLaMA (arXiv) models and run inference. In order to download the checkpoints and tokenizer, fill this google form

In a conda env with pytorch / cuda available, run

pip install -r requirements.txt

Then in this repository

pip install -e .

Once your request is approved, you will receive links to download the tokenizer and model files. Edit the download.sh script with the signed url provided in the email to download the model weights and tokenizer.

The provided example.py can be run on a single or multi-gpu node with torchrun and will output completions for two pre-defined prompts. Using TARGET_FOLDER as defined in download.sh:

torchrun --nproc_per_node MP example.py --ckpt_dir $TARGET_FOLDER/model_size --tokenizer_path $TARGET_FOLDER/tokenizer.model

Different models require different MP values:

• 1. The download.sh script doesn't work on default bash in MacOS X
• 2. Generations are bad!
• 3. CUDA Out of memory errors
• 4. Other languages

See MODEL_CARD.md

See the LICENSE file.