Instructions to use neoai-inc/Llama-3-neoAI-8B-Chat-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neoai-inc/Llama-3-neoAI-8B-Chat-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="neoai-inc/Llama-3-neoAI-8B-Chat-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neoai-inc/Llama-3-neoAI-8B-Chat-v0.1")
model = AutoModelForCausalLM.from_pretrained("neoai-inc/Llama-3-neoAI-8B-Chat-v0.1")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use neoai-inc/Llama-3-neoAI-8B-Chat-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neoai-inc/Llama-3-neoAI-8B-Chat-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neoai-inc/Llama-3-neoAI-8B-Chat-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neoai-inc/Llama-3-neoAI-8B-Chat-v0.1

SGLang

How to use neoai-inc/Llama-3-neoAI-8B-Chat-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 "neoai-inc/Llama-3-neoAI-8B-Chat-v0.1" \
    --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": "neoai-inc/Llama-3-neoAI-8B-Chat-v0.1",
		"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 "neoai-inc/Llama-3-neoAI-8B-Chat-v0.1" \
        --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": "neoai-inc/Llama-3-neoAI-8B-Chat-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use neoai-inc/Llama-3-neoAI-8B-Chat-v0.1 with Docker Model Runner:
```
docker model run hf.co/neoai-inc/Llama-3-neoAI-8B-Chat-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama 3 neoAI 8B Chat v0.1

Model Description

Llama 3 neoAI 8B Chat v0.1は，Meta-Llama-3-8B-Instructをベースとして日本語能力を強化するために事後学習を行なったモデルです．

詳細はブログ記事を参照してください．

Evaluation

Usage

Huggingface

import transformers
import torch

model_id = "neoai-inc/Llama-3-neoAI-8B-Chat-v0.1"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "あなたは誠実で優秀な日本人のアシスタントです。"},
    {"role": "user", "content": "日本で一番高い山は？"},
]

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    messages,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][-1])

License

Developed by

Developers

以下アルファベット順

How to Cite

@misc{neoAI-Llama3-8B-Chat-v0.1, 
      title={Llama-3-neoAI-8B-Chat-v0.1}, 
      url={https://huggingface.co/neoai-inc/Llama-3-neoAI-8B-Chat-v0.1}, 
      author={Gouki Minegishi and Koki Itai and Koshiro Terasawa and Masaki Otsuki and Ryo Yagi},
      year={2024},
}

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for neoai-inc/Llama-3-neoAI-8B-Chat-v0.1

Merges

1 model

Quantizations

5 models

Collection including neoai-inc/Llama-3-neoAI-8B-Chat-v0.1

neoAI LLM

Collection

1 item • Updated Jun 26, 2024 • 1