Instructions to use aixsatoshi/Llama-3-youko-8b-instruct-chatvector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aixsatoshi/Llama-3-youko-8b-instruct-chatvector with Transformers:

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

pipe = pipeline("text-generation", model="aixsatoshi/Llama-3-youko-8b-instruct-chatvector")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aixsatoshi/Llama-3-youko-8b-instruct-chatvector")
model = AutoModelForCausalLM.from_pretrained("aixsatoshi/Llama-3-youko-8b-instruct-chatvector")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use aixsatoshi/Llama-3-youko-8b-instruct-chatvector with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aixsatoshi/Llama-3-youko-8b-instruct-chatvector"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aixsatoshi/Llama-3-youko-8b-instruct-chatvector",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aixsatoshi/Llama-3-youko-8b-instruct-chatvector

SGLang

How to use aixsatoshi/Llama-3-youko-8b-instruct-chatvector 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 "aixsatoshi/Llama-3-youko-8b-instruct-chatvector" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aixsatoshi/Llama-3-youko-8b-instruct-chatvector",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "aixsatoshi/Llama-3-youko-8b-instruct-chatvector" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aixsatoshi/Llama-3-youko-8b-instruct-chatvector",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aixsatoshi/Llama-3-youko-8b-instruct-chatvector with Docker Model Runner:
```
docker model run hf.co/aixsatoshi/Llama-3-youko-8b-instruct-chatvector
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

youko-8bは、追加の日本語継続事前学習により日本語が大変流暢なLlama-3です。
Instructionモデルとの差分ベクトルマージを行いました。

rinna/llama-3-youko-8b + 0.8*(meta-llama/Meta-Llama-3-8B-Instruct - meta-llama/Meta-Llama-3-8B)

詳細はrinna/llama-3-youko-8bをご確認ください。

Downloads last month: 12

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for aixsatoshi/Llama-3-youko-8b-instruct-chatvector

Merges

2 models

Quantizations

1 model

aixsatoshi
/

Llama-3-youko-8b-instruct-chatvector

Model tree for aixsatoshi/Llama-3-youko-8b-instruct-chatvector

Spaces using aixsatoshi/Llama-3-youko-8b-instruct-chatvector 9