Instructions to use Locutusque/TinyMistral-248M-v2-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/TinyMistral-248M-v2-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/TinyMistral-248M-v2-Instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/TinyMistral-248M-v2-Instruct")
model = AutoModelForCausalLM.from_pretrained("Locutusque/TinyMistral-248M-v2-Instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Locutusque/TinyMistral-248M-v2-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/TinyMistral-248M-v2-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/TinyMistral-248M-v2-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/TinyMistral-248M-v2-Instruct

SGLang

How to use Locutusque/TinyMistral-248M-v2-Instruct 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 "Locutusque/TinyMistral-248M-v2-Instruct" \
    --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": "Locutusque/TinyMistral-248M-v2-Instruct",
		"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 "Locutusque/TinyMistral-248M-v2-Instruct" \
        --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": "Locutusque/TinyMistral-248M-v2-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/TinyMistral-248M-v2-Instruct with Docker Model Runner:
```
docker model run hf.co/Locutusque/TinyMistral-248M-v2-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Description

Fine-tuned Locutusque/TinyMistral-248M-v2 on the HuggingFaceH4/ultrachat_200k dataset.

Recommended inference parameters

do_sample: true
temperature: 0.1
top_p: 0.14
top_k: 12
repetition_penalty: 1.1

Recommended prompt template

<|im_start|>user\n{user message}<|im_end|>\n<|im_start|>assistant\n{assistant message}<|endoftext|>

Evaluation

This model will be submitted to the Open LLM Leaderboard.

Downloads last month: 855

Safetensors

Model size

0.2B params

Tensor type

F16

Model tree for Locutusque/TinyMistral-248M-v2-Instruct

Base model

Locutusque/TinyMistral-248M-v2

Finetuned

(1)

this model

Merges

2 models

Quantizations

3 models

Locutusque
/

TinyMistral-248M-v2-Instruct

Description

Recommended inference parameters

Recommended prompt template

Evaluation

Model tree for Locutusque/TinyMistral-248M-v2-Instruct

Dataset used to train Locutusque/TinyMistral-248M-v2-Instruct