metadata
base_model: openai/gpt-oss-20b
library_name: transformers
tags:
- lora
- sft
- tool-use
- gpt-oss
license: apache-2.0
gpt-oss-claude-code
Fine-tuned openai/gpt-oss-20b for tool-use and agentic coding tasks. LoRA adapters merged into base weights.
Quick start
import re, torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"deburky/gpt-oss-claude-code",
torch_dtype=torch.bfloat16,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("deburky/gpt-oss-claude-code")
messages = [{"role": "user", "content": "Who is Alan Turing?"}]
inputs = tokenizer.apply_chat_template(
messages, add_generation_prompt=True,
return_tensors="pt", return_dict=True,
).to(model.device)
with torch.no_grad():
out = model.generate(**inputs, max_new_tokens=256)
response = tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:])
if "<|channel|>final<|message|>" in response:
response = response.split("<|channel|>final<|message|>")[-1]
print(re.sub(r"<\\|[^>]+\\|>", "", response).strip())
Apple Silicon (MLX)
A fused MLX version is available at deburky/gpt-oss-claude-mlx.
Training
- Data: ~280 tool-use conversation examples in gpt-oss harmony format
- Method: LoRA (rank 8, alpha 16) on attention + MoE expert layers, merged after training
- LR: 1e-4, cosine schedule
- Final val loss: ~0.48
- Hardware: Google Colab