---
base_model: unsloth/gpt-oss-20b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gpt_oss
license: apache-2.0
language:
- en
---

# Finetuned GPT_OSS Model

- **Developed by:** Sai1290

- text-generation-inference
- transformers
- unsloth
- gpt_oss
- **License:** Apache-2.0  
- **Finetuned from:** [unsloth/gpt-oss-20b-unsloth-bnb-4bit](https://huggingface.co/unsloth/gpt-oss-20b-unsloth-bnb-4bit)

This GPT_OSS model was finetuned with accelerated training (2x faster) using [Unsloth](https://github.com/unslothai/unsloth) and Hugging Face's [TRL](https://github.com/huggingface/transformers/tree/main/examples/research_projects/trl) library for reinforcement learning.


## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Sai1290/gpt-oss-finetune"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example generation
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))