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")

# 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")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

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 (35)

Access request FAQ

#21 opened almost 2 years ago by

Request for clarification on repeated rejection of access request

#198 opened 13 days ago by

Need access

#197 opened 16 days ago by

need access

#196 opened about 1 month ago by

Request: DOI

#195 opened about 1 month ago by

Request: DOI

#194 opened about 1 month ago by

Request: DOI

#193 opened about 1 month ago by

AshishPatel4886

Request: DOI

#192 opened about 1 month ago by

Access Request

#191 opened about 2 months ago by deleted

Reset my access request

#190 opened about 2 months ago by deleted

Update README.md

#189 opened about 2 months ago by

Access Request

#188 opened about 2 months ago by

Xotiic-Official

Request for Access: Academic Research Purpose

#186 opened 2 months ago by

Request Wanted

#185 opened 2 months ago by

Request : DOI

#184 opened 2 months ago by

Request : DOI

#183 opened 2 months ago by

fix: set `clean_up_tokenization_spaces` to `false`

#182 opened 2 months ago by

Request: DOI

#181 opened 2 months ago by

Request to reopen access request for Llama 3.1-8B

#180 opened 3 months ago by deleted

Install & run meta-llama/Llama-3.1-8B easily using llmpm

#179 opened 3 months ago by

Access Request

#178 opened 3 months ago by deleted

PetAI

#177 opened 3 months ago by

Access request

#174 opened 3 months ago by

Access

#173 opened 4 months ago by

Request Access

#172 opened 4 months ago by

Request: DOI

#171 opened 4 months ago by

Re-evaluation for model access.

#170 opened 4 months ago by

Request for Re-evaluation: Llama 3.1 Access

#169 opened 4 months ago by

6 degree

#168 opened 4 months ago by

Request: DOI

#167 opened 5 months ago by

Report

#166 opened 5 months ago by

roagrawal

#164 opened 6 months ago by

Delay Giving Permission

#162 opened 6 months ago by

Request: DOI

#161 opened 7 months ago by

sdff

#160 opened 7 months ago by

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

#159 opened 8 months ago by

Need model for Learning

#157 opened 8 months ago by

Request: DOI

#156 opened 8 months ago by

Access request denied?

#155 opened 8 months ago by

Request: DOI

#154 opened 8 months ago by

VLLM curl call error

#153 opened 9 months ago by

Rejected

#152 opened 9 months ago by

Request: DOI - Request for Access (Access Denied)

#151 opened 9 months ago by

Request: DOI

#150 opened 9 months ago by

Request to access repo denied

#149 opened 9 months ago by

Request: DOI

#148 opened 9 months ago by

One possible reason getting rejected

#147 opened 10 months ago by

Access to repo rejected.

#146 opened 10 months ago by

preferablehuman

Access to Meta LLaMA Models — Request Rejected, No Reapply Option

#145 opened 10 months ago by

Model Request for Llama 3.1 Family of Models Rejected

#144 opened 10 months ago by