Instructions to use tokyotech-llm/Llama-3-Swallow-70B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tokyotech-llm/Llama-3-Swallow-70B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="tokyotech-llm/Llama-3-Swallow-70B-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tokyotech-llm/Llama-3-Swallow-70B-v0.1")
model = AutoModelForCausalLM.from_pretrained("tokyotech-llm/Llama-3-Swallow-70B-v0.1")

Inference
Local Apps Settings

vLLM

How to use tokyotech-llm/Llama-3-Swallow-70B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tokyotech-llm/Llama-3-Swallow-70B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokyotech-llm/Llama-3-Swallow-70B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tokyotech-llm/Llama-3-Swallow-70B-v0.1

SGLang

How to use tokyotech-llm/Llama-3-Swallow-70B-v0.1 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 "tokyotech-llm/Llama-3-Swallow-70B-v0.1" \
    --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": "tokyotech-llm/Llama-3-Swallow-70B-v0.1",
		"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 "tokyotech-llm/Llama-3-Swallow-70B-v0.1" \
        --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": "tokyotech-llm/Llama-3-Swallow-70B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tokyotech-llm/Llama-3-Swallow-70B-v0.1 with Docker Model Runner:
```
docker model run hf.co/tokyotech-llm/Llama-3-Swallow-70B-v0.1
```

Llama-3-Swallow-70B-v0.1 / model-00008-of-00030.safetensors

okoge

Upload model-00008-of-00030.safetensors

114f786 verified about 2 years ago

Download

History Blame

5 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 8c124ecb0f8b36e4707a7d05da80aa5e5b3db061ddc03d9cdbfba72803228316
Size of remote file:: 5 GB
SHA256:: 4412287717f5147ec8defca8ee60e51345ffda228e0a956d175d272cd2d9665e

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.