mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-10-01 01:26:03 -04:00
46 lines
1.6 KiB
Markdown
46 lines
1.6 KiB
Markdown
LLaMA is a Large Language Model developed by Meta AI.
|
|
|
|
It was trained on more tokens than previous models. The result is that the smallest version with 7 billion parameters has similar performance to GPT-3 with 175 billion parameters.
|
|
|
|
This guide will cover usage through the official `transformers` implementation. For 4-bit mode, head over to [GPTQ models (4 bit mode)
|
|
](GPTQ-models-(4-bit-mode).md).
|
|
|
|
## Getting the weights
|
|
|
|
### Option 1: pre-converted weights
|
|
|
|
* Torrent: https://github.com/oobabooga/text-generation-webui/pull/530#issuecomment-1484235789
|
|
* Direct download: https://huggingface.co/Neko-Institute-of-Science
|
|
|
|
⚠️ The tokenizers for the Torrent source above and also for many LLaMA fine-tunes available on Hugging Face may be outdated, so I recommend downloading the following universal LLaMA tokenizer:
|
|
|
|
```
|
|
python download-model.py oobabooga/llama-tokenizer
|
|
```
|
|
|
|
Once downloaded, it will be automatically applied to **every** `LlamaForCausalLM` model that you try to load.
|
|
|
|
### Option 2: convert the weights yourself
|
|
|
|
1. Install the `protobuf` library:
|
|
|
|
```
|
|
pip install protobuf==3.20.1
|
|
```
|
|
|
|
2. Use the script below to convert the model in `.pth` format that you, a fellow academic, downloaded using Meta's official link:
|
|
|
|
### [convert_llama_weights_to_hf.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py)
|
|
|
|
```
|
|
python convert_llama_weights_to_hf.py --input_dir /path/to/LLaMA --model_size 7B --output_dir /tmp/outputs/llama-7b
|
|
```
|
|
|
|
3. Move the `llama-7b` folder inside your `text-generation-webui/models` folder.
|
|
|
|
## Starting the web UI
|
|
|
|
```python
|
|
python server.py --model llama-7b
|
|
```
|