Instructions to use okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf with Transformers:

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

pipe = pipeline("text-generation", model="okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf

SGLang

How to use okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf 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 "okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf" \
    --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": "okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf",
		"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 "okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf" \
        --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": "okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf with Docker Model Runner:
```
docker model run hf.co/okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf
```

Llama-3.3-Swallow-70B-Instruct-v0.4-imatrix-gguf - Built with Llama

このモデルは、Llama-3.3-Swallow-70B-Instruct-v0.4をOllamaで利用できるようにgguf形式に変換して量子化を行ったものです。

量子化は、imatrixを利用して行いました。imatrixの生成のデータセットはTFMC/imatrix-dataset-for-japanese-llmを利用しました。

imatrixを利用した量子化については、llama.cpp/examples/imatrixをご覧ください。

License

META LLAMA 3.3 COMMUNITY LICENSE and Gemma Terms of Use

上記のLlama-3.3-Swallow-70Bのライセンスに従いご利用ください。本モデルを利用して発生した如何なる不利益や損害について、作成者は責任を負わないものとします。

Downloads last month: 8

GGUF

Hardware compatibility

4-bit

Model tree for okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf

Base model

tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4

Quantized

(9)

this model

okamototk
/

Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf

Llama-3.3-Swallow-70B-Instruct-v0.4-imatrix-gguf - Built with Llama

License

Model tree for okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf

Dataset used to train okamototk/Llama-3.1-Swallow-8B-Instruct-v0.3-imatrix-gguf