Instructions to use JackFram/llama-160m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JackFram/llama-160m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JackFram/llama-160m")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("JackFram/llama-160m") model = AutoModelForCausalLM.from_pretrained("JackFram/llama-160m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use JackFram/llama-160m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JackFram/llama-160m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JackFram/llama-160m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/JackFram/llama-160m
- SGLang
How to use JackFram/llama-160m 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 "JackFram/llama-160m" \ --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": "JackFram/llama-160m", "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 "JackFram/llama-160m" \ --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": "JackFram/llama-160m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use JackFram/llama-160m with Docker Model Runner:
docker model run hf.co/JackFram/llama-160m
Commit History
-
Update README.md
aca9b68
-
align_with_llama2 (#12)
- align tokenizer with llama 2 (53e9c9a2483d0068b1810a0294f9269d7d0f6d12) Co-authored-by: Gabriele Oliaro <goliaro@users.noreply.huggingface.co>2780869 -
Fix bos_token_id to match BOS from tokenizer.model file (#11)
- Fix bos_token_id to match BOS from tokenizer.model file (c2feb19e64fc1f085538ef52ad56c37b5d753725) Co-authored-by: Gabriele Oliaro <goliaro@users.noreply.huggingface.co>a57a4d3
-
Update special_tokens_map.json (#10)
- Update special_tokens_map.json (294e30d7d40aaf032d81a408b0e3f46add18c65c) Co-authored-by: Arthur Zucker <ArthurZ@users.noreply.huggingface.co>dbb6ca4
-
Fix tokenizer_config.json (#9)
- Fix tokenizer_config.json (bdf71d72a993cb6046c08dc83148406911045a4b) Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>d1a656d
-
Upload folder using huggingface_hub
59bb272
-
Adding `safetensors` variant of this model (#8)
- Adding `safetensors` variant of this model (fad252046e73e22f4d34f63a111479f8bed64e14) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>4f4621a -
Update README.md
b6ff1b8
-
Upload folder using huggingface_hub
a741c30
-
Upload folder using huggingface_hub
8142e69
-
Upload folder using huggingface_hub
e7f67b9
-
Upload folder using huggingface_hub
91cf7f2
-
Upload folder using huggingface_hub
f46cc31 -
Upload folder using huggingface_hub
1143504 -
Upload folder using huggingface_hub
af24d3b
-
Update README.md
a71ec1f
-
Upload folder using huggingface_hub
e8cda94
-
Update README.md
a3619ca
-
Update config.json
545654b -
Upload with huggingface_hub
bf33fb3 -
Update README.md
c2cfbdb -
initial commit
420b501