Instructions to use Bobblack225/MiniMa3bFinetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bobblack225/MiniMa3bFinetune with Transformers:

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

pipe = pipeline("text-generation", model="Bobblack225/MiniMa3bFinetune")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Bobblack225/MiniMa3bFinetune")
model = AutoModelForCausalLM.from_pretrained("Bobblack225/MiniMa3bFinetune", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Bobblack225/MiniMa3bFinetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bobblack225/MiniMa3bFinetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bobblack225/MiniMa3bFinetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Bobblack225/MiniMa3bFinetune

SGLang

How to use Bobblack225/MiniMa3bFinetune 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 "Bobblack225/MiniMa3bFinetune" \
    --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": "Bobblack225/MiniMa3bFinetune",
		"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 "Bobblack225/MiniMa3bFinetune" \
        --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": "Bobblack225/MiniMa3bFinetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Bobblack225/MiniMa3bFinetune with Docker Model Runner:
```
docker model run hf.co/Bobblack225/MiniMa3bFinetune
```

This is a simple fine-tuning of MiniMa on a dataset of chatgpt interactions. More info to come shortly after though testing. Derived from MiniMa which is derived from Llama 2. Anything built on this must follow the License for Llama 2.

Very unstable, thus I neglected to include the tokenizer. If you really want to use this, you must use MiniMa's tokenizer. I would advise giving me a few days to get this up and running fully.

Downloads last month: 9

Safetensors

Model size

3B params

Tensor type

F32