qwen25-logql-finetune-v1.2.0

qwen25-logql-finetune-v1.2.0

Fine-tuned Gemma 3 12B for LogQL Query Generation [MLC]

This model is fine-tuned from Google's Gemma 3 12B to generate LogQL queries from natural language descriptions.

Model Information

• Base Model: gemma-3-12b
• Quantization: q4f16_1
• Format: MLC (Machine Learning Compilation)
• Use Case: LogQL query generation

Training Details

• Base model: gemma/gemma-3-12b-it
• Fine-tuned for LogQL query generation
• Trained on custom generated dataset (15000 samples, 5 epochs)

Usage

With MLC-LLM Python API

from mlc_llm import MLCEngine

# Create engine
engine = MLCEngine(
    model="NiekWork/qwen25-logql-finetune-v1.2.0",
    mode="local"
)

# Generate text
response = engine.chat.completions.create(
    messages=[
        
    ]
)

print(response.choices[0].message.content)

With MLC-LLM CLI

mlc_llm chat NiekWork/qwen25-logql-finetune-v1.2.0

Files

This repository contains:

• mlc-chat-config.json - MLC configuration
• ndarray-cache.json - Weight metadata
• params_shard_*.bin - Quantized model weights
• tokenizer.json - Tokenizer
• tokenizer_config.json - Tokenizer configuration

About MLC-LLM

MLC LLM is a universal solution that allows any language model to be deployed natively on diverse hardware backends and native applications. More info at: https://llm.mlc.ai/

License

This model is released under the Apache 2.0 license.