Instructions to use LLM360/Amber with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM360/Amber with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LLM360/Amber")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LLM360/Amber") model = AutoModelForCausalLM.from_pretrained("LLM360/Amber") - Inference
- Local Apps Settings
- vLLM
How to use LLM360/Amber with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LLM360/Amber" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM360/Amber", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LLM360/Amber
- SGLang
How to use LLM360/Amber 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 "LLM360/Amber" \ --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": "LLM360/Amber", "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 "LLM360/Amber" \ --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": "LLM360/Amber", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LLM360/Amber with Docker Model Runner:
docker model run hf.co/LLM360/Amber
| { | |
| "results": { | |
| "hellaswag": { | |
| "acc": 0.5476000796654052, | |
| "acc_stderr": 0.0049671185759052865, | |
| "acc_norm": 0.7382991435968931, | |
| "acc_norm_stderr": 0.004386622589119069 | |
| } | |
| }, | |
| "versions": { | |
| "hellaswag": 0 | |
| }, | |
| "config": { | |
| "model": "hf-causal", | |
| "model_args": "pretrained=./workdir_7b_16mix/ckpt_359", | |
| "num_fewshot": 10, | |
| "batch_size": "1", | |
| "batch_sizes": [], | |
| "device": null, | |
| "no_cache": true, | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "description_dict": {} | |
| } | |
| } |