Instructions to use GreenBitAI/LLaMA-3B-2bit-groupsize8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GreenBitAI/LLaMA-3B-2bit-groupsize8 with Transformers:

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

pipe = pipeline("text-generation", model="GreenBitAI/LLaMA-3B-2bit-groupsize8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GreenBitAI/LLaMA-3B-2bit-groupsize8")
model = AutoModelForCausalLM.from_pretrained("GreenBitAI/LLaMA-3B-2bit-groupsize8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GreenBitAI/LLaMA-3B-2bit-groupsize8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GreenBitAI/LLaMA-3B-2bit-groupsize8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GreenBitAI/LLaMA-3B-2bit-groupsize8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GreenBitAI/LLaMA-3B-2bit-groupsize8

SGLang

How to use GreenBitAI/LLaMA-3B-2bit-groupsize8 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 "GreenBitAI/LLaMA-3B-2bit-groupsize8" \
    --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": "GreenBitAI/LLaMA-3B-2bit-groupsize8",
		"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 "GreenBitAI/LLaMA-3B-2bit-groupsize8" \
        --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": "GreenBitAI/LLaMA-3B-2bit-groupsize8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GreenBitAI/LLaMA-3B-2bit-groupsize8 with Docker Model Runner:
```
docker model run hf.co/GreenBitAI/LLaMA-3B-2bit-groupsize8
```

NicoNico6 commited on Aug 15, 2023

Commit

183df74

1 Parent(s): 1defb2c

add 2bit llama3b model

Browse files

Files changed (4) hide show

config.json +1 -0
generation_config.json +1 -0
special_tokens_map.json +1 -0
tokenizer.model +1 -0

config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ ../../blobs/573ed2e85bc147201714680570c20d7d5506c1f4

generation_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ ../../blobs/737a363761e41a11a1575fe06b90729fdb7ed2b5

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ ../../blobs/1c141cfedc26fa17771e88d0a1372d4a7387a3ec

tokenizer.model ADDED Viewed

	@@ -0,0 +1 @@


1	+ ../../blobs/ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b