GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
khadim-hussain
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
khadim-hussain
Model Tree
openai/gpt-oss-20b
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "khadim-hussain/gpt-oss-20b-stem-reasoning-merged", torch_dtype="auto", device_map="auto", trust_remote_code=True,)tokenizer = AutoTokenizer.from_pretrained( "khadim-hussain/gpt-oss-20b-stem-reasoning-merged", trust_remote_code=True,) # GPT-OSS uses Harmony formatprompt = """<|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))| Property | Value |
|---|---|
| Base Model | openai/gpt-oss-20b |
| Type | Merged (LoRA merged into base weights) |
| Size | ~41GB (bf16) |
| Parameters | 21B total, 3.6B active (MoE) |
| Format | OpenAI Harmony |
| Training | QLoRA fine-tuning on STEM Q&A dataset |
GPT-OSS uses the OpenAI Harmony format with channels:
<|channel|>analysis - Chain-of-thought reasoning (thinking)<|channel|>final - Final user-facing responseExample output:
text
<|start|>assistant<|channel|>analysis<|message|>DNA stands for deoxyribonucleic acid. It is a molecule...<|end|><|start|>assistant<|channel|>final<|message|>DNA is a molecule that carries genetic instructions used in growth, development, and reproduction.<|return|>| Metric | Value |
|---|---|
| Train Loss | 1.087 |
| Eval Loss | 0.837 |
| Training Examples | 4,260 |
| Evaluation Examples | 474 |
| Epochs | 1 |
A GGUF quantized version (Q8_0, ~21GB) is available for use with Ollama/llama.cpp:
bash
# Using Ollamaollama run khadim-hussain/gpt-oss-20b-stem-reasoningSee: khadim-hussain/gpt-oss-20b-stem-reasoning-GGUF
If you use this model, please cite:
bibtex
@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-merged}}Also cite the original GPT-OSS model:
bibtex
@misc{openai2025gptoss, author = {OpenAI}, title = {GPT-OSS: Open-Weight Language Models}, year = {2025}, url = {https://github.com/openai/gpt-oss}}Apache 2.0 (inherited from GPT-OSS)
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "khadim-hussain/gpt-oss-20b-stem-reasoning-merged", torch_dtype="auto", device_map="auto", trust_remote_code=True,)tokenizer = AutoTokenizer.from_pretrained( "khadim-hussain/gpt-oss-20b-stem-reasoning-merged", trust_remote_code=True,) # GPT-OSS uses Harmony formatprompt = """<|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))<|start|>assistant<|channel|>analysis<|message|>DNA stands for deoxyribonucleic acid. It is a molecule...<|end|><|start|>assistant<|channel|>final<|message|>DNA is a molecule that carries genetic instructions used in growth, development, and reproduction.<|return|># Using Ollamaollama run khadim-hussain/gpt-oss-20b-stem-reasoning@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-merged}}@misc{openai2025gptoss, author = {OpenAI}, title = {GPT-OSS: Open-Weight Language Models}, year = {2025}, url = {https://github.com/openai/gpt-oss}}