Instructions to use DataPilot/Llama3.1-ArrowSE-v0.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DataPilot/Llama3.1-ArrowSE-v0.4 with Transformers:

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

pipe = pipeline("text-generation", model="DataPilot/Llama3.1-ArrowSE-v0.4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DataPilot/Llama3.1-ArrowSE-v0.4")
model = AutoModelForCausalLM.from_pretrained("DataPilot/Llama3.1-ArrowSE-v0.4")
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 DataPilot/Llama3.1-ArrowSE-v0.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DataPilot/Llama3.1-ArrowSE-v0.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DataPilot/Llama3.1-ArrowSE-v0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DataPilot/Llama3.1-ArrowSE-v0.4

SGLang

How to use DataPilot/Llama3.1-ArrowSE-v0.4 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 "DataPilot/Llama3.1-ArrowSE-v0.4" \
    --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": "DataPilot/Llama3.1-ArrowSE-v0.4",
		"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 "DataPilot/Llama3.1-ArrowSE-v0.4" \
        --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": "DataPilot/Llama3.1-ArrowSE-v0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DataPilot/Llama3.1-ArrowSE-v0.4 with Docker Model Runner:
```
docker model run hf.co/DataPilot/Llama3.1-ArrowSE-v0.4
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

概要

このモデルはllama3.1-8B-instructをもとに日本語性能を高めることを目的にMergekit&ファインチューニングを用いて作成されました。

meta,ELYZA,nvidiaの皆様に感謝します。

how to use

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

DEFAULT_SYSTEM_PROMPT = "あなたは誠実で優秀な日本人のアシスタントです。特に指示が無い場合は、常に日本語で回答してください。"
text = "Vtuberとして成功するために大切な5つのことを小学生にでもわかるように教えてください。"

model_name = "DataPilot/Llama3.1-ArrowSE-v0.4"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
)
model.eval()

messages = [
    {"role": "system", "content": DEFAULT_SYSTEM_PROMPT},
    {"role": "user", "content": text},
]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
token_ids = tokenizer.encode(
    prompt, add_special_tokens=False, return_tensors="pt"
)

with torch.no_grad():
    output_ids = model.generate(
        token_ids.to(model.device),
        max_new_tokens=1200,
        do_sample=True,
        temperature=0.6,
        top_p=0.9,
    )
output = tokenizer.decode(
    output_ids.tolist()[0][token_ids.size(1):], skip_special_tokens=True
)
print(output)

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using meta-llama/Meta-Llama-3.1-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: meta-llama/Meta-Llama-3.1-8B-Instruct
    parameters:
      weight: 1
  - model: elyza/Llama-3-ELYZA-JP-8B
    parameters:
      weight: 0.7
  - model: nvidia/Llama3-ChatQA-1.5-8B
    parameters:
      weight: 0.15
merge_method: ties
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
parameters:
  normalize: false
dtype: bfloat16