Instructions to use NeuronUz/MustaqiLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeuronUz/MustaqiLLM with Transformers:

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

pipe = pipeline("text-generation", model="NeuronUz/MustaqiLLM", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("NeuronUz/MustaqiLLM", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NeuronUz/MustaqiLLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeuronUz/MustaqiLLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeuronUz/MustaqiLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NeuronUz/MustaqiLLM

SGLang

How to use NeuronUz/MustaqiLLM 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 "NeuronUz/MustaqiLLM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeuronUz/MustaqiLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "NeuronUz/MustaqiLLM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeuronUz/MustaqiLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NeuronUz/MustaqiLLM with Docker Model Runner:
```
docker model run hf.co/NeuronUz/MustaqiLLM
```

kmamaroziqov commited on 7 days ago

Commit

022c915

verified ·

1 Parent(s): 30e8f3b

Drop contamination check section

Browse files

Files changed (1) hide show

README.md +0 -18

README.md CHANGED Viewed

@@ -219,24 +219,6 @@ Random baselines: 0.25 for the 4-way MCQ tasks, 0.10 for news, 0.50 for sentimen
 | Xorijiy Yangiliklar (World news) | 11,732 | 0.5124 |
 | Oila va Jamiyat (Family & Society) | 14,012 | 0.4273 |
-### Contamination check
-44.1% of the sentiment evaluation set also appears in the training data, because the
-benchmark scores the dataset's `train` split and the task-format training rows were drawn
-from the same pool. This was tested rather than assumed:
-| slice | n | score |
-|---|---:|---:|
-| items seen in training | 1,200 | 0.9342 |
-| items not seen (exact match excluded) | 1,200 | 0.9300 |
-| items not seen (exact **and** normalized match excluded) | 1,500 | 0.9347 |
-Performance on strictly unseen data is identical to performance on memorized data, so
-the sentiment score reflects genuine capability. The news benchmark has **zero** overlap
-with training data.
----
 ## Limitations
 **Multiple-choice knowledge tasks perform at chance.** uzlib, MMLU-Uz and MMLU-English

 | Xorijiy Yangiliklar (World news) | 11,732 | 0.5124 |
 | Oila va Jamiyat (Family & Society) | 14,012 | 0.4273 |
 ## Limitations
 **Multiple-choice knowledge tasks perform at chance.** uzlib, MMLU-Uz and MMLU-English