---

base_model:
    - Qwen/Qwen3-0.6B
    - meta-llama/Llama-3.2-1B
library_name: transformers
pipeline_tag: text-classification
tags:
    - qwen3
    - llama-3.2
    - gguf
    - onnx
    - safetensors
    - llama.cpp
    - onnxruntime
    - intent-classification
    - text-classification
license: apache-2.0

---

# Intent Classifier (Release)

This Hugging Face repo contains only the final released models for the
intent-classifier project.

It is intentionally limited to release artifacts:

- merged full-weight model checkpoints
- GGUF exports for llama.cpp
- ONNX exports for runtime backends.

## Current release

Current stable release: **v1.0**
To use this exact release, select `v1.0` in the Files and versions tab or load the repo with `revision="v1.0"`.

## Models

- qwen3-0.6b
- llama3.2-1b

Both models are fine-tuned for intent classification and exported in multiple inference formats.

- **Transformers / Safetensors:** Full-weight Hugging Face checkpoints for standard Transformers inference and downstream conversion.
- **GGUF:** GGUF files are provided for llama.cpp inference.
- **ONNX:** ONNX exports are provided for runtime backends.

## Transformers / Safetensors

The Transformers folders contain merged full-weight checkpoints in safetensors format.

These are the canonical Hugging Face model artifacts for each selected release model and are the best starting point if you want to:

- run inference with Transformers,
- inspect tokenizer and config files,
- convert to another serving format,
- fine-tune further from the released checkpoint.

## GGUF

The GGUF files are intended for inference with [llama.cpp](https://github.com/ggml-org/llama.cpp).

Available quantization formats include:

- Q4_K_M
- Q6_K
- Q8_0
- F16

## ONNX

The ONNX folders contain exported model variants for ONNX Runtime backends.

These artifacts are intended for deployment and benchmarking across runtimes such as CPU, CoreML, CUDA, or TensorRT pipelines, depending on the exported variant.

When available, the ONNX exports may include multiple precision or quantization variants such as fp16 or int8.

## Versioning

Stable releases are published as git tags such as `v1.0`.
The README describes the latest intended stable release, while the Files and versions tab lets you browse or load a specific tagged revision.

## Repository structure

```text
intent-classifier/
├── qwen3-0.6b/
│   ├── Transformers / Safetensors
│   ├── GGUF
│   └── ONNX
│
├── llama3.2-1b/
│   ├── Transformers / Safetensors
│   ├── GGUF
│   └── ONNX
│
└── README.md
```

## Related repositories

Training code and experiment artifacts are maintained separately.

- Training code: <https://github.com/kon172verma/intent-classifier>
- Inference/benchmarking: <https://github.com/kon172verma/intent-classifier-inference>
- Experiments (all adapters): <https://huggingface.co/kon172verma/intent-classifier-experiments>