Instructions to use Mitake/llama3.1_good_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mitake/llama3.1_good_model with Transformers:

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

pipe = pipeline("text-generation", model="Mitake/llama3.1_good_model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mitake/llama3.1_good_model")
model = AutoModelForCausalLM.from_pretrained("Mitake/llama3.1_good_model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mitake/llama3.1_good_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mitake/llama3.1_good_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mitake/llama3.1_good_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mitake/llama3.1_good_model

SGLang

How to use Mitake/llama3.1_good_model 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 "Mitake/llama3.1_good_model" \
    --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": "Mitake/llama3.1_good_model",
		"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 "Mitake/llama3.1_good_model" \
        --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": "Mitake/llama3.1_good_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use Mitake/llama3.1_good_model with Docker Model Runner:
```
docker model run hf.co/Mitake/llama3.1_good_model
```

llama3.1_good_model

Commit History

Apr 1, 2025

03:07
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
72aa5f6
03:03
Trained with Unsloth

Mitake

Verified signature
5e70558
02:52
Upload tokenizer

Mitake

Verified signature
64e2456
02:52
Upload README.md with huggingface_hub

Mitake

Verified signature
ae28db6
02:52
initial commit

Mitake

Verified signature
61a39d5

Commit History

Apr 1, 2025

Adding `safetensors` variant of this model⁠

Trained with Unsloth

Upload tokenizer

Upload README.md with huggingface_hub

initial commit