from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "your-username/gpt-oss-20b-fine-tuned"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

inputs = tokenizer("Your prompt here", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Details

This model was fine-tuned using Unsloth for efficient training and inference.

Requirements

transformers>=4.30.0
torch>=2.0.0
accelerate

mogalaman251100/gpt-oss-20b-fine-tuned

GPT-OSS 20B Fine-tuned Model

Model Details

Usage

Training Details

Requirements

mogalaman251100/
gpt-oss-20b-fine-tuned