Instructions to use AlexWortega/smallstral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AlexWortega/smallstral with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AlexWortega/smallstral")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AlexWortega/smallstral") model = AutoModelForCausalLM.from_pretrained("AlexWortega/smallstral") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AlexWortega/smallstral with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AlexWortega/smallstral" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AlexWortega/smallstral", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AlexWortega/smallstral
- SGLang
How to use AlexWortega/smallstral 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 "AlexWortega/smallstral" \ --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": "AlexWortega/smallstral", "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 "AlexWortega/smallstral" \ --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": "AlexWortega/smallstral", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AlexWortega/smallstral with Docker Model Runner:
docker model run hf.co/AlexWortega/smallstral
Smallstral, layer pruned Mistral
| Task | Metric | Mistral-7B-v0.1 Value | Smallstral Value |
|---|---|---|---|
| hendrycksTestRu-high_school_mathematics | acc | 0.3037 | 0.2852 |
| hendrycksTestRu-high_school_microeconomics | acc | 0.3950 | 0.3319 |
| hendrycksTestRu-high_school_physics | acc | 0.3113 | 0.2649 |
| hendrycksTestRu-high_school_psychology | acc | 0.5193 | 0.1945 |
| hendrycksTestRu-high_school_statistics | acc | 0.3241 | 0.4028 |
| hendrycksTestRu-high_school_us_history | acc | 0.5392 | 0.2451 |
| hendrycksTestRu-high_school_world_history | acc | 0.5781 | 0.2321 |
| hendrycksTestRu-human_aging | acc | 0.4843 | 0.3184 |
| parus | acc | 0.5000 | 0.4875 |
| rcb | acc | 0.3653 | 0.3288 |
| rcb | f1_macro | 0.3313 | 0.1691 |
| rwsd | acc | 0.4917 | 0.4901 |
- Downloads last month
- 4
docker model run hf.co/AlexWortega/smallstral