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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/TinyMistral-248M")
model = AutoModelForCausalLM.from_pretrained("Locutusque/TinyMistral-248M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/TinyMistral-248M"
# 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",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

Docker Model Runner
How to use Locutusque/TinyMistral-248M with Docker Model Runner:
```
docker model run hf.co/Locutusque/TinyMistral-248M
```

Locutusque commited on Nov 14, 2023

Commit

544cbf0

1 Parent(s): 8f970b3

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -6,4 +6,4 @@ language:
 - en
 pipeline_tag: text-generation
 ---
-A pretrained language model based on the Mistral 7B model, shrunk to about 248 million parameters. Minimal training was needed for this model, with only 250,000 examples over 125,000 steps required for convergence.

 - en
 pipeline_tag: text-generation
 ---
+A pre-trained language model based on the Mistral 7B model, shrunk to approximately 248 million parameters, required minimal training. Convergence was achieved with only 250,000 examples over 125,000 steps. This model is not intended for direct use but rather for fine-tuning on a downstream task.