Instructions to use khadim-hussain/gpt-oss-20b-stem-reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use khadim-hussain/gpt-oss-20b-stem-reasoning with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gpt-oss-20b-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "khadim-hussain/gpt-oss-20b-stem-reasoning")

Transformers

How to use khadim-hussain/gpt-oss-20b-stem-reasoning with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="khadim-hussain/gpt-oss-20b-stem-reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("khadim-hussain/gpt-oss-20b-stem-reasoning", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use khadim-hussain/gpt-oss-20b-stem-reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "khadim-hussain/gpt-oss-20b-stem-reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "khadim-hussain/gpt-oss-20b-stem-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/khadim-hussain/gpt-oss-20b-stem-reasoning

SGLang

How to use khadim-hussain/gpt-oss-20b-stem-reasoning with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "khadim-hussain/gpt-oss-20b-stem-reasoning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "khadim-hussain/gpt-oss-20b-stem-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "khadim-hussain/gpt-oss-20b-stem-reasoning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "khadim-hussain/gpt-oss-20b-stem-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use khadim-hussain/gpt-oss-20b-stem-reasoning with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for khadim-hussain/gpt-oss-20b-stem-reasoning to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for khadim-hussain/gpt-oss-20b-stem-reasoning to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for khadim-hussain/gpt-oss-20b-stem-reasoning to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="khadim-hussain/gpt-oss-20b-stem-reasoning",
    max_seq_length=2048,
)

Docker Model Runner
How to use khadim-hussain/gpt-oss-20b-stem-reasoning with Docker Model Runner:
```
docker model run hf.co/khadim-hussain/gpt-oss-20b-stem-reasoning
```

GPT-OSS-20B STEM Reasoning (LoRA Adapter)

This is a LoRA adapter fine-tuned on OpenAI's GPT-OSS-20B for STEM reasoning tasks using the Harmony response format.

Author: Khadim Hussain

For the merged full model (larger download, standalone use), see: khadim-hussain/gpt-oss-20b-stem-reasoning-merged

Model Description

Base Model: openai/gpt-oss-20b
Type: LoRA Adapter (QLoRA 4-bit)
Format: OpenAI Harmony format with analysis (thinking) and final channels
Training: Fine-tuned on STEM Q&A dataset with chain-of-thought reasoning

Usage

from unsloth import FastLanguageModel

# Load model with adapter
model, tokenizer = FastLanguageModel.from_pretrained(
    "khadim-hussain/gpt-oss-20b-stem-reasoning",
    max_seq_length=2048,
    load_in_4bit=True,
)

# Format prompt using Harmony format
prompt = """<|start|>system<|message|>You are a helpful assistant trained by OpenAI.

Reasoning: medium

# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>user<|message|>What is DNA?<|end|><|start|>assistant"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=False))

Harmony Response Format

GPT-OSS uses the OpenAI Harmony format with channels:

<|channel|>analysis - Chain-of-thought reasoning (thinking)
<|channel|>final - Final user-facing response

Example output:

<|start|>assistant<|channel|>analysis<|message|>DNA stands for deoxyribonucleic acid...<|end|>
<|start|>assistant<|channel|>final<|message|>DNA is a molecule that carries genetic instructions...<|return|>

Training Details

Metric	Value
Train Loss	1.087
Eval Loss	0.837
Training Examples	4,260
Evaluation Examples	474
Epochs	1
LoRA Rank	32
LoRA Alpha	64

Training Configuration

Method: QLoRA (4-bit quantization)
Optimizer: AdamW 8-bit
Learning Rate: 1e-4
Batch Size: 1 (with gradient accumulation 16)
Framework: Unsloth + TRL

GGUF Version

A GGUF quantized version (Q8_0, ~21GB) is available for use with Ollama/llama.cpp:

See: khadim-hussain/gpt-oss-20b-stem-reasoning-GGUF

Acknowledgments

OpenAI - GPT-OSS-20B base model
Unsloth - Fast fine-tuning framework
Hugging Face - TRL, PEFT, Transformers
llama.cpp - GGUF conversion tools

Citation

If you use this model, please cite:

@misc{hussain2026gptoss-stem,
  author = {Hussain, Khadim},
  title = {GPT-OSS-20B STEM Reasoning: Fine-tuned for Science Q&A with Chain-of-Thought},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/khadim-hussain/gpt-oss-20b-stem-reasoning}
}

Also cite the original GPT-OSS model:

@misc{openai2025gptoss,
  author = {OpenAI},
  title = {GPT-OSS: Open-Weight Language Models},
  year = {2025},
  url = {https://github.com/openai/gpt-oss}
}

License

Apache 2.0 (inherited from GPT-OSS)

Downloads last month: 3

Model tree for khadim-hussain/gpt-oss-20b-stem-reasoning

Base model

openai/gpt-oss-20b

Adapter

(227)

this model