Instructions to use GAIR/Abel-7B-002 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GAIR/Abel-7B-002 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GAIR/Abel-7B-002")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GAIR/Abel-7B-002") model = AutoModelForCausalLM.from_pretrained("GAIR/Abel-7B-002", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use GAIR/Abel-7B-002 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GAIR/Abel-7B-002" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GAIR/Abel-7B-002", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GAIR/Abel-7B-002
- SGLang
How to use GAIR/Abel-7B-002 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 "GAIR/Abel-7B-002" \ --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": "GAIR/Abel-7B-002", "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 "GAIR/Abel-7B-002" \ --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": "GAIR/Abel-7B-002", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GAIR/Abel-7B-002 with Docker Model Runner:
docker model run hf.co/GAIR/Abel-7B-002
Download pytorch_model-00003-of-00003.bin from GAIR/Abel-7B-002: direct link, hf CLI and curl.
- Browser
- Download file 9.08 GB
-
https://huggingface.co/GAIR/Abel-7B-002/resolve/main/pytorch_model-00003-of-00003.bin
- Command line
-
hf download hf://GAIR/Abel-7B-002/pytorch_model-00003-of-00003.bin
-
curl -L -o pytorch_model-00003-of-00003.bin https://huggingface.co/GAIR/Abel-7B-002/resolve/main/pytorch_model-00003-of-00003.bin
9.08 GB
- Xet hash:
- 5ba11e5ddb0f546baa5ec82cdb090d2558a59316a607a22c2d8f3541ef5f48ab
- Size of remote file:
- 9.08 GB
- SHA256:
- b09098cfdcec6381db0dbabb68706477b36488161d5a5a897350c78d35372edd
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.