Instructions to use thunlp/LLaMA3.2-Instruct-1B-FR-Spec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thunlp/LLaMA3.2-Instruct-1B-FR-Spec with Transformers:

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

pipe = pipeline("text-generation", model="thunlp/LLaMA3.2-Instruct-1B-FR-Spec")

# Load model directly
from transformers import AutoTokenizer, LlamaForCausalLMEagle

tokenizer = AutoTokenizer.from_pretrained("thunlp/LLaMA3.2-Instruct-1B-FR-Spec")
model = LlamaForCausalLMEagle.from_pretrained("thunlp/LLaMA3.2-Instruct-1B-FR-Spec")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use thunlp/LLaMA3.2-Instruct-1B-FR-Spec with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thunlp/LLaMA3.2-Instruct-1B-FR-Spec"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thunlp/LLaMA3.2-Instruct-1B-FR-Spec",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/thunlp/LLaMA3.2-Instruct-1B-FR-Spec

SGLang

How to use thunlp/LLaMA3.2-Instruct-1B-FR-Spec 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 "thunlp/LLaMA3.2-Instruct-1B-FR-Spec" \
    --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": "thunlp/LLaMA3.2-Instruct-1B-FR-Spec",
		"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 "thunlp/LLaMA3.2-Instruct-1B-FR-Spec" \
        --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": "thunlp/LLaMA3.2-Instruct-1B-FR-Spec",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thunlp/LLaMA3.2-Instruct-1B-FR-Spec with Docker Model Runner:
```
docker model run hf.co/thunlp/LLaMA3.2-Instruct-1B-FR-Spec
```

Improve model card: Add license, library name and pipeline tag

by nielsr HF Staff - opened Mar 8, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

nielsr

Mar 8, 2025

This PR improves the model card by adding the missing license, library_name and pipeline_tag.

Improve model card: Add license, library name and pipeline tagbee0e8d0

thunlp changed pull request status to merged Jul 8, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment