Open-Orca/OpenOrca
Viewer • Updated • 2.94M • 49.3k • 1.54k
How to use Nbardy/micro-mistral with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Nbardy/micro-mistral") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Nbardy/micro-mistral")
model = AutoModelForCausalLM.from_pretrained("Nbardy/micro-mistral")How to use Nbardy/micro-mistral with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nbardy/micro-mistral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Nbardy/micro-mistral",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Nbardy/micro-mistral
How to use Nbardy/micro-mistral with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Nbardy/micro-mistral" \
--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": "Nbardy/micro-mistral",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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/micro-mistral" \
--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": "Nbardy/micro-mistral",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Nbardy/micro-mistral with Docker Model Runner:
docker model run hf.co/Nbardy/micro-mistral
Micro Mistral
A small version of mistral.
Similiar to some of the small llama variants, but uses GQA, tied embeddings, and sliding window attention.
Dataset Minipile Instruct Math OpenOrca Synthetic Data
TODO: Complete Dataset section
docker model run hf.co/Nbardy/micro-mistral