metadata
library_name: transformers
base_model: Qwen/Qwen2.5-0.5B-Instruct
tags:
- text-generation
- json
- classification
- catllm
license: apache-2.0
language:
- en
pipeline_tag: text-generation
CatLLM JSON Formatter
A fine-tuned Qwen2.5-0.5B-Instruct model that converts messy LLM classification output into valid cat-llm JSON format.
Task
Given a list of numbered categories and raw (possibly malformed) classification output from another LLM, this model produces clean JSON:
{"1": "0", "2": "1", "3": "0", ...}
Usage
This model is used automatically by cat-llm when json_formatter=True:
import catllm as cat
results = cat.classify(
input_data=df["responses"],
categories=["Positive", "Negative", "Neutral"],
api_key="your-key",
json_formatter=True, # enables the formatter fallback
)
Install the formatter dependencies: pip install cat-llm[formatter]
Training
- Base model: Qwen/Qwen2.5-0.5B-Instruct
- Method: LoRA (r=16, alpha=32) merged into base weights
- Training data: 4,000 synthetic examples covering 26+ messy output formats
- Epochs: 3
- Metrics: 100% parse success, 98% exact match on held-out test set
Prompt Format
The model uses the Qwen chat template with:
System: JSON formatter instructions (built into cat-llm)
User:
Categories:
1. Category A
2. Category B
...
Raw classification output:
{messy output here}
Assistant: {"1":"0","2":"1",...}