Instructions to use JackFram/llama-160m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JackFram/llama-160m-base with Transformers:

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

pipe = pipeline("text-generation", model="JackFram/llama-160m-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JackFram/llama-160m-base")
model = AutoModelForCausalLM.from_pretrained("JackFram/llama-160m-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JackFram/llama-160m-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JackFram/llama-160m-base"
# 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-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JackFram/llama-160m-base

SGLang

How to use JackFram/llama-160m-base 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-base" \
    --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-base",
		"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-base" \
        --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-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JackFram/llama-160m-base with Docker Model Runner:
```
docker model run hf.co/JackFram/llama-160m-base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model description

This is a LLaMA-like model with only 160M parameters trained on Wikipedia and part of the C4-en and C4-realnewslike datasets.

No evaluation has been conducted yet, so use it with care.

The model is mainly developed as a base Small Speculative Model in the SpecInfer paper.

Citation

To cite the model, please use

@misc{miao2023specinfer,
      title={SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification}, 
      author={Xupeng Miao and Gabriele Oliaro and Zhihao Zhang and Xinhao Cheng and Zeyu Wang and Rae Ying Yee Wong and Zhuoming Chen and Daiyaan Arfeen and Reyna Abhyankar and Zhihao Jia},
      year={2023},
      eprint={2305.09781},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 2

Safetensors

Model size

0.2B params

Tensor type

F32

Model tree for JackFram/llama-160m-base

Quantizations

1 model

Dataset used to train JackFram/llama-160m-base

Paper for JackFram/llama-160m-base

SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification

Paper • 2305.09781 • Published May 16, 2023 • 4