Instructions to use ainowmk/MK-LLM-Mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ainowmk/MK-LLM-Mistral with Transformers:

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

pipe = pipeline("text-generation", model="ainowmk/MK-LLM-Mistral")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ainowmk/MK-LLM-Mistral")
model = AutoModelForCausalLM.from_pretrained("ainowmk/MK-LLM-Mistral", device_map="auto")

PEFT
How to use ainowmk/MK-LLM-Mistral with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ainowmk/MK-LLM-Mistral with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ainowmk/MK-LLM-Mistral

SGLang

How to use ainowmk/MK-LLM-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 "ainowmk/MK-LLM-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": "ainowmk/MK-LLM-Mistral",
		"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 "ainowmk/MK-LLM-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": "ainowmk/MK-LLM-Mistral",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ainowmk/MK-LLM-Mistral with Docker Model Runner:
```
docker model run hf.co/ainowmk/MK-LLM-Mistral
```

MK-LLM-Mistral / examples /client_python.py

ainow-mk

Upload 65 files

f29d474 verified 10 months ago

Raw

History Blame Contribute Delete

1.06 kB

	import os
	import requests


	base_url = os.getenv("OPENAI_BASE_URL", "http://localhost:8000/v1")
	api_key = os.getenv("OPENAI_API_KEY", "dummy")


	def chat_stream():
	url = f"{base_url}/chat/completions"
	payload = {
	"model": "mk-llm",
	"messages": [
	{"role": "system", "content": "Ти си помошник кој зборува на македонски."},
	{"role": "user", "content": "Која е историјата на Охрид?"},
	],
	"stream": True,
	}
	headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
	with requests.post(url, headers=headers, json=payload, stream=True) as r:
	for line in r.iter_lines():
	if not line:
	continue
	if line.startswith(b"data: "):
	chunk = line[len(b"data: "):]
	if chunk == b"[DONE]":
	break
	print(chunk.decode("utf-8"))


	if __name__ == "__main__":
	chat_stream()