---
title: LeChatonFat
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/LeChatonFat"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/LeChatonFat.md"
repository: AI-ModelScope/LeChatonFat
last_updated: 2026-07-14
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mistral3
architectures:
  - Mistral3ForConditionalGeneration
base_model:
  - mistralai/Ministral-3-3B-Instruct-2512-BF16
base_model_relation: finetune
parameters: 3.8B
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - gguf
  - safetensors
frameworks:
  - pytorch
language:
  - en
  - fr
downloads: 83
stars: 0
tags:
  - chat
  - assistant
  - persona
  - mistral
---

# LeChatonFat

> LeChatonFat - AI-ModelScope 在 ModelScope 开源的模型。Guys this model its my respect for meme about Le Chaton Fat model from Mistral AI, surely benchmarks not real like not real this model or any Le Chaton Fat models

AI-ModelScope/LeChatonFat 是 ModelScope 魔搭社区上的 3.8B 参数text-generation模型，采用 apache-2.0 许可，基于 mistralai/Ministral-3-3B-Instruct-2512-BF16 构建。

- **Repository**: AI-ModelScope/LeChatonFat
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 3.8B
- **Base model**: mistralai/Ministral-3-3B-Instruct-2512-BF16
- **Tags**: chat, assistant, persona, mistral
- **Downloads**: 83
- **Stars**: 0
- **Last updated**: 2026-07-14

Source: https://www.modelscope.cn/models/AI-ModelScope/LeChatonFat

---

# Le Chaton Fat 🐱

Guys this model its my respect for meme about Le Chaton Fat model from Mistral AI, surely benchmarks not real like not real this model or any Le Chaton Fat models

![le1](https://cdn-uploads.huggingface.co/production/uploads/67329d3f69fded92d56ab41a/phL2p_g5OFGhEaGg5NoKH.jpeg)

![le2](https://cdn-uploads.huggingface.co/production/uploads/67329d3f69fded92d56ab41a/rQPotqDIZ8-rT2fTTa6zT.jpeg)

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tok = AutoTokenizer.from_pretrained("squ11z1/LeChatonFat")
model = AutoModelForCausalLM.from_pretrained("squ11z1/LeChatonFat", dtype=torch.bfloat16, device_map="cuda")
msgs = [{"role": "user", "content": "Who are you?"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to("cuda")
print(tok.decode(model.generate(ids, max_new_tokens=128)[0], skip_special_tokens=True))
```

## License
Inherits the base model's license (Apache-2.0).

***God bless AI***