Instructions to use Bitsy/llama-7b-hfcompatible-clean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bitsy/llama-7b-hfcompatible-clean with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Bitsy/llama-7b-hfcompatible-clean")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Bitsy/llama-7b-hfcompatible-clean")
model = AutoModelForCausalLM.from_pretrained("Bitsy/llama-7b-hfcompatible-clean")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Bitsy/llama-7b-hfcompatible-clean with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bitsy/llama-7b-hfcompatible-clean"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bitsy/llama-7b-hfcompatible-clean",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Bitsy/llama-7b-hfcompatible-clean

SGLang

How to use Bitsy/llama-7b-hfcompatible-clean with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Bitsy/llama-7b-hfcompatible-clean" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bitsy/llama-7b-hfcompatible-clean",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Bitsy/llama-7b-hfcompatible-clean" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bitsy/llama-7b-hfcompatible-clean",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Bitsy/llama-7b-hfcompatible-clean with Docker Model Runner:
```
docker model run hf.co/Bitsy/llama-7b-hfcompatible-clean
```

Create README.md

by Delcos - opened Mar 10, 2023

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-0

Files changed (1) hide show

README.md +5 -0

README.md ADDED Viewed

	@@ -0,0 +1,5 @@

+Simply use this model as you would any other now. Below is an example:
+tokenizer = transformers.LLaMATokenizer.from_pretrained("Bitsy/Not-LLaMA-7B-Pytorch-Transformer-Compatible")
+model = transformers.LLaMAForCausalLM.from_pretrained("Bitsy/Not-LLaMA-7B-Pytorch-Transformer-Compatible")