Instructions to use GreenBitAI/LLaMA-7B-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GreenBitAI/LLaMA-7B-2bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GreenBitAI/LLaMA-7B-2bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GreenBitAI/LLaMA-7B-2bit") model = AutoModelForCausalLM.from_pretrained("GreenBitAI/LLaMA-7B-2bit") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use GreenBitAI/LLaMA-7B-2bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GreenBitAI/LLaMA-7B-2bit" # 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-7B-2bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GreenBitAI/LLaMA-7B-2bit
- SGLang
How to use GreenBitAI/LLaMA-7B-2bit 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-7B-2bit" \ --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-7B-2bit", "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-7B-2bit" \ --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-7B-2bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GreenBitAI/LLaMA-7B-2bit with Docker Model Runner:
docker model run hf.co/GreenBitAI/LLaMA-7B-2bit
Joseph Bethge commited on
Commit ·
e064a2b
1
Parent(s): ee85511
add link to alpaca version
Browse files
README.md
CHANGED
|
@@ -5,4 +5,6 @@ license: apache-2.0
|
|
| 5 |
|
| 6 |
This is GreenBitAI's pretrained **2-bit** LLaMA model with extreme compression yet still strong performance.
|
| 7 |
|
|
|
|
|
|
|
| 8 |
Please refer to our [Github page](https://github.com/GreenBitAI/low_bit_llama) for the code to run the model and more information.
|
|
|
|
| 5 |
|
| 6 |
This is GreenBitAI's pretrained **2-bit** LLaMA model with extreme compression yet still strong performance.
|
| 7 |
|
| 8 |
+
There are instruction-tuned LoRA parameters available [here](https://huggingface.co/GreenBitAI/LLaMA-7B-2bit-alpaca).
|
| 9 |
+
|
| 10 |
Please refer to our [Github page](https://github.com/GreenBitAI/low_bit_llama) for the code to run the model and more information.
|