GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
artindnr
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
artindnr
Model Tree
openai/gpt-oss-20b
Input Modalities
Output Modalities
Supported Functionality
This is a LoRA adapter only — it is not a merged/standalone model. You need the base openai/gpt-oss-20b weights plus this adapter to run it. The repo contains:
adapter_config.jsonadapter_model.safetensorsFine-tuned on HuggingFaceH4/Multilingual-Thinking, a reasoning dataset built by sampling 1k training examples from the SystemChat subset of SmolTalk2 and translating the chain-of-thought traces into Spanish, French, Italian, and German using another language model. The English reasoning traces are also retained, so the model sees the same underlying reasoning task expressed across five languages.
This setup is intended to encourage the model to produce coherent step-by-step reasoning regardless of the input/output language, rather than reasoning only in English and translating the final answer.
0.19.1| Parameter | Value |
|---|---|
r (rank) | 8 |
lora_alpha | 16 |
lora_dropout | 0.0 |
bias | none |
target_modules | q_proj, k_proj, v_proj, |
The adapter targets both the standard attention projections and a subset of the mixture-of-experts (MoE) expert weights at layers 7, 15, and 23 — chosen to adapt reasoning-relevant expert pathways at early, middle, and late points in the network without fine-tuning all experts.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torchbase_model_id = "openai/gpt-oss-20b"adapter_id = "artindnr/gpt-oss-20b-multilingual-thinking"tokenizer = AutoTokenizer.from_pretrained(adapter_id)base_model = AutoModelForCausalLM.from_pretrained(base_model_id,torch_dtype=torch.bfloat16,device_map="auto",)model = PeftModel.from_pretrained(base_model, adapter_id)messages = [{"role": "user", "content": "Explique el teorema de Pitágoras paso a paso."}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)outputs = model.generate(inputs, max_new_tokens=512)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
python
from unsloth import FastLanguageModelmodel, tokenizer = FastLanguageModel.from_pretrained(model_name = "artindnr/gpt-oss-20b-multilingual-thinking",max_seq_length = 1024,dtype = None,load_in_4bit = True,)FastLanguageModel.for_inference(model)messages = [{"role": "user", "content": "Explique el teorema de Pitágoras paso a paso."}]inputs = tokenizer.apply_chat_template(messages,add_generation_prompt = True,return_tensors = "pt",return_dict = True,).to("cuda")from transformers import TextStreamer_ = model.generate(**inputs, max_new_tokens = 512, streamer = TextStreamer(tokenizer))
Note: this adapter was trained with plain PEFT (not Unsloth's trainer), using PEFT's
target_parametersfeature to target specific MoE expert layers directly. Loading through Unsloth should work since it loads adapters via standard PEFT under the hood, but the PEFT/Transformers path above is the one this card's usage was verified against — if you hit a loading issue with Unsloth, fall back to Option 1.
This adapter is intended for research and experimentation on multilingual reasoning in LLMs. It is not evaluated for production or safety-critical use cases.
If you use this adapter, please also credit the base model and dataset:
bibtex
@misc{gpt-oss-20b,title = {gpt-oss-20b},author = {OpenAI},howpublished = {\url{https://huggingface.co/openai/gpt-oss-20b}}}@misc{multilingual-thinking,title = {Multilingual-Thinking},author = {HuggingFaceH4},howpublished = {\url{https://huggingface.co/datasets/HuggingFaceH4/Multilingual-Thinking}}}
Fine-tuned and maintained by Artin Daneshvar GitHub: github.com/Artin200912
o_projtarget_parameters | MoE expert layers: gate_up_proj, down_proj on layers 7, 15, and 23 |