Sai1290/gpt-oss-finetune

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

This GPT_OSS model was finetuned with accelerated training (2x faster) using Unsloth and Hugging Face's TRL library for reinforcement learning.

Usage

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]))