---
title: Gemma-2b-it-FT-Code
canonical_url: "https://www.modelscope.cn/models/Kukedlc/Gemma-2b-it-FT-Code"
md_url: "https://www.modelscope.cn/models/Kukedlc/Gemma-2b-it-FT-Code.md"
repository: Kukedlc/Gemma-2b-it-FT-Code
last_updated: 2026-06-01
license: apache-2.0
model_type:
  - gemma
architectures:
  - GemmaForCausalLM
parameters: 2.5B
tensor_type:
  - F16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 15
stars: 0
---

# Gemma-2b-it-FT-Code

> Gemma-2b-it-FT-Code - Kukedlc 在 ModelScope 开源的模型。Gemma 2b fine-tuned for programming & data science.

Kukedlc/Gemma-2b-it-FT-Code 是 ModelScope 魔搭社区上的 2.5B 参数机器学习模型，采用 apache-2.0 许可。

- **Repository**: Kukedlc/Gemma-2b-it-FT-Code
- **License**: apache-2.0
- **Parameters**: 2.5B
- **Downloads**: 15
- **Stars**: 0
- **Last updated**: 2026-06-01

Source: https://www.modelscope.cn/models/Kukedlc/Gemma-2b-it-FT-Code

---

# Gemma 2b fine-tuned for programming & data science.

![](https://raw.githubusercontent.com/kukedlc87/imagenes/main/DALL%C2%B7E%202023-12-31%2003.39.25%20-%20An%20image%20of%20a%20robot%20copywriter%20working%20in%20a%20modern%20office%20setting.%20The%20robot%20has%20a%20sleek%2C%20humanoid%20design%20with%20metallic%20surfaces%20and%20digital%20eyes%2C%20sit.png)

Dataset: MagiCoder


## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/Gemma-2b-it-FT-Code"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```