meta-llama
/

Llama-3.1-8B

Text Generation

text-generation-inference

Model card Files Files and versions

Instructions to use meta-llama/Llama-3.1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.1-8B with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-8B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use meta-llama/Llama-3.1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-3.1-8B"
# 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-3.1-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.1-8B

How to use meta-llama/Llama-3.1-8B 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-3.1-8B" \
    --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-3.1-8B",
		"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-3.1-8B" \
        --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-3.1-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use meta-llama/Llama-3.1-8B with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.1-8B
```

Resources

View closed (37)

Access request FAQ

#21 opened about 2 years ago by

Request to reset rejected access request for Llama-3.1-8B

#213 opened 6 days ago by

Request for Reconsideration of Access to Llama 3.1 8B

#212 opened 16 days ago by

Request still pending

#211 opened 26 days ago by

Request to Reset Llama 3.1 8B Access

#210 opened about 1 month ago by

Access Request for Llama-3.1-8B Please

#209 opened about 2 months ago by

Request for manual review of rejected Llama 3.1 access

#208 opened 2 months ago by

test

#207 opened 3 months ago by

Request to reset model access - Typo / Region mismatch

#205 opened 3 months ago by

Request to reset gated access status / typo in form

#204 opened 3 months ago by deleted

TemporalMesh Transformer: 29.4 PPL at 48% compute — dynamic graph attention + adaptive exit gates (open-source, 226 tests)

#202 opened 4 months ago by

Add EvalEval community eval results

#201 opened 4 months ago by

Access Request

#200 opened 4 months ago by

Need access

#199 opened 4 months ago by

Request for clarification on repeated rejection of access request

#198 opened 5 months ago by

Need access

#197 opened 5 months ago by

need access

#196 opened 6 months ago by

Request: DOI

#195 opened 6 months ago by

Request: DOI

#194 opened 6 months ago by

Request: DOI

#193 opened 6 months ago by

AshishPatel4886

Request: DOI

#192 opened 6 months ago by

Access Request

#191 opened 6 months ago by deleted

Reset my access request

#190 opened 6 months ago by deleted

Update README.md

#189 opened 6 months ago by

Access Request

#188 opened 6 months ago by

Xotiic-Official

Request for Access: Academic Research Purpose

#186 opened 7 months ago by

Request Wanted

#185 opened 7 months ago by

Request : DOI

#184 opened 7 months ago by

Request : DOI

#183 opened 7 months ago by

fix: set `clean_up_tokenization_spaces` to `false`

#182 opened 7 months ago by

Request: DOI

#181 opened 7 months ago by

Request to reopen access request for Llama 3.1-8B

#180 opened 7 months ago by deleted

Access Request

#178 opened 7 months ago by deleted

PetAI

#177 opened 7 months ago by

Access request

#174 opened 8 months ago by

Access

#173 opened 8 months ago by

Request Access

#172 opened 8 months ago by

Request: DOI

#171 opened 9 months ago by

Re-evaluation for model access.

#170 opened 9 months ago by

Request for Re-evaluation: Llama 3.1 Access

#169 opened 9 months ago by

6 degree

#168 opened 9 months ago by

Request: DOI

#167 opened 9 months ago by

Report

#166 opened 10 months ago by

roagrawal

#164 opened 11 months ago by

Delay Giving Permission

#162 opened 11 months ago by

Request: DOI

#161 opened 11 months ago by

sdff

#160 opened 12 months ago by

my request to access LLama 3.1 model has been rejected , i want to re-apply

#159 opened 12 months ago by

Need model for Learning

#157 opened about 1 year ago by

Request: DOI

#156 opened about 1 year ago by