Instructions to use Nbardy/mini-mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nbardy/mini-mistral with Transformers:

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

pipe = pipeline("text-generation", model="Nbardy/mini-mistral")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nbardy/mini-mistral")
model = AutoModelForCausalLM.from_pretrained("Nbardy/mini-mistral")
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 Nbardy/mini-mistral with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Nbardy/mini-mistral

SGLang

How to use Nbardy/mini-mistral 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 "Nbardy/mini-mistral" \
    --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": "Nbardy/mini-mistral",
		"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 "Nbardy/mini-mistral" \
        --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": "Nbardy/mini-mistral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nbardy/mini-mistral with Docker Model Runner:
```
docker model run hf.co/Nbardy/mini-mistral
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Micro Mistral

This is a small mistral model with 6 layers

It is similar to smol llama varaints uses GQA and tied embeddings. Except it uses mistral style arch with GQA and sliding window attention

This architecture takes GQA and tied embeddings to create an effeceint 0.5B model that uses the mistral architecture(It is supported in downstream applications)

Dataset

Minipile Instruct Math OpenOrca Synthetic Data

TODO: Complete Dataset section

Downloads last month: 4