---
library_name: transformers
license: mit
base_model: Qwen/Qwen3-4B
datasets:
  - kxdw2580/catgirl-dataset
language:
  - zh
tags:
- llama-factory
- catgirl
- generated_from_trainer
pipeline_tag: text-generation
model-index:
- name: Qwen3-4B-CatGirl
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Qwen3-4B-sft

This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the catgirl-create-v2-qwen3, the catgirl-common-v2-qwen3 and the catgirl-neo-v2-qwen3 datasets.

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 9

### Training results



### Framework versions

- Transformers 4.52.4
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1