You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
41 lines
1.2 KiB
Markdown
41 lines
1.2 KiB
Markdown
# Inference LLaMA models using CPU only
|
|
|
|
This repository is intended as a minimal, hackable and readable example to load [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) ([arXiv](https://arxiv.org/abs/2302.13971v1)) models and run inference.
|
|
In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jk851eBVbX1m5TAv5)
|
|
|
|
### Setup
|
|
In a conda env with pytorch / cuda available, run
|
|
```
|
|
pip install -r requirements.txt
|
|
```
|
|
Then in this repository
|
|
```
|
|
pip install -e .
|
|
```
|
|
|
|
### Download
|
|
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.
|
|
|
|
### CPU Inference
|
|
Place tokenizer.model and tokenizer_checklist.chk into /tokenizer folder
|
|
|
|
Place three files of 7B model into /model folder
|
|
|
|
Run it:
|
|
```
|
|
python example-cpu.py
|
|
```
|
|
|
|
### FAQ
|
|
- [1. The download.sh script doesn't work on default bash in MacOS X](FAQ.md#1)
|
|
- [2. Generations are bad!](FAQ.md#2)
|
|
- [3. CUDA Out of memory errors](FAQ.md#3)
|
|
- [4. Other languages](FAQ.md#4)
|
|
|
|
### Model Card
|
|
See [MODEL_CARD.md](MODEL_CARD.md)
|
|
|
|
### License
|
|
See the [LICENSE](LICENSE) file.
|