meta-llama
/

Llama-3.2-3B

Text Generation

text-generation-inference

Model card Files Files and versions

Instructions to use meta-llama/Llama-3.2-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.2-3B with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.2-3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use meta-llama/Llama-3.2-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-3.2-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.2-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.2-3B

How to use meta-llama/Llama-3.2-3B 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 "meta-llama/Llama-3.2-3B" \
    --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": "meta-llama/Llama-3.2-3B",
		"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 "meta-llama/Llama-3.2-3B" \
        --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": "meta-llama/Llama-3.2-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use meta-llama/Llama-3.2-3B with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.2-3B
```

Resources

View closed (20)

Access request

#88 opened about 1 month ago by

TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture

#87 opened about 2 months ago by

Access request

#85 opened about 2 months ago by

Add EvalEval community eval results

#84 opened about 2 months ago by

Access request

#83 opened 2 months ago by

Access request

#82 opened 2 months ago by

Access request for TRIBE v2 research and educational use

#81 opened 2 months ago by

Access request for educational purposes

#80 opened 3 months ago by

Access Request

#79 opened 3 months ago by

Access Request

#78 opened 3 months ago by

Requesting Access

#77 opened 3 months ago by

Access denied

#76 opened 3 months ago by

Access Request

#75 opened 3 months ago by

Request for Access to meta-llama/Llama-3.2-3B for Academic Research

#74 opened 3 months ago by

Access Request

#73 opened 4 months ago by

Access please

#72 opened 4 months ago by

Access Request

#71 opened 4 months ago by

Access request

#70 opened 4 months ago by

Request Access

#69 opened 4 months ago by

Request to re-evaluate access for [dr777] - Research on Neuroscience Visualization

#68 opened 4 months ago by

Access

#67 opened 4 months ago by

Access Request

#65 opened 4 months ago by

fix: set `clean_up_tokenization_spaces` to `false`

#64 opened 4 months ago by

Access needed

#63 opened 4 months ago by

Need access to the repo

#61 opened 6 months ago by

Access Please

#60 opened 10 months ago by

model meta-llama/Llama-3.2-1B-Instruc

#59 opened 11 months ago by

Request: DOI

#58 opened 11 months ago by

Access needed

#57 opened 11 months ago by

Access for model

#56 opened 11 months ago by

Request for Access

#55 opened 11 months ago by

Request for model access

#54 opened 12 months ago by

PLEASE I Need Access to the Llama 3 Collections

#53 opened about 1 year ago by

I Need Access to Llama 3.2-3B Model

#52 opened about 1 year ago by

Your request to access this repo has been rejected by the repo's authors.

#51 opened about 1 year ago by

Request rejected

#50 opened about 1 year ago by

Request: DOI

#49 opened about 1 year ago by

Request: DOI

#48 opened about 1 year ago by

Request: DOI

#47 opened about 1 year ago by

Request: DOI

#45 opened about 1 year ago by

Please grant me the permission for Llama-3.2-3B for project purpose.

#44 opened over 1 year ago by

ashishmukka2112

please grant access to meta-llama/Llama-3.2-3B for personal research demand

#43 opened over 1 year ago by

Mir fehlt die tokenizer.model

#42 opened over 1 year ago by

Upload 344473.gif

#41 opened over 1 year ago by

Please provide access to llama3.2-3B model, I want to perform a poc

#40 opened over 1 year ago by

Request: DOI

#39 opened over 1 year ago by

Access for personal research

#38 opened over 1 year ago by

RuntimeError: The size of tensor a (24) must match the size of tensor b (128) at non-singleton dimension 3

#37 opened over 1 year ago by

Access Rejected

#36 opened over 1 year ago by

Request: DOI

#35 opened over 1 year ago by