---
library_name: transformers
license: apache-2.0
language: [en]
base_model: openai/gpt-oss-120b
pipeline_tag: text-generation
tags:
  - aurora
  - alcf
  - hpc
  - intel-gpu
  - oneapi
  - sycl
---

# gpt-oss-120B-Aurora-Chat v3

LoRA fine-tune of [`openai/gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) specialized for the
[**ALCF Aurora supercomputer**](https://docs.alcf.anl.gov/aurora/) (Intel Xeon Sapphire
Rapids + Intel GPU Max 1550 / Ponte Vecchio, oneAPI / SYCL, PBS Pro).

Off-the-shelf code-LLMs hallucinate Aurora specifics — they suggest `nvcc` instead of
`icpx -fsycl`, `srun` / `aprun` instead of `mpiexec`, NERSC's `/global/cfs` instead of
`/lus/flare`, and CUDA device strings instead of `xpu`. This adapter teaches the base
model the actual Aurora toolchain, file system layout, scheduler conventions, and
recommended PyTorch/TensorFlow/SYCL idioms.

## Model summary

| | |
|---|---|
| **Base model** | [`openai/gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) |
| **Format** | Merged 16-bit — HuggingFace Transformers / vLLM / TGI |
| **Fine-tuning** | LoRA (PEFT) — r=32, α=64, dropout 0.0, 2 epochs |
| **Optimizer** | AdamW fused, lr 2e-4 cosine, warmup 3%, batch 1 × grad-accum 8 |
| **Precision / seq-len** | bf16, 1,536 tokens |
| **Training data** | [`aurora-docs-distill-multirank`](https://github.com/SIslamMun/Generator/tree/aurora-datasets-2026-04-30/datasets/aurora/iter2/data/training/A) — 4,495 ChatML rows |
| **Train loss (final)** | 0.4800 |
| **Hardware** | Aurora node, model-parallel across 1–12 PVC tiles via HF `device_map='auto'`, IPEX + PyTorch 2.10 XPU backend |
| **Eval (53-Q Aurora, 0–5)** | pending |

## Quick start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tok = AutoTokenizer.from_pretrained("shazzadulimun/gpt-oss-120b-aurora-chat-v3")
mdl = AutoModelForCausalLM.from_pretrained("shazzadulimun/gpt-oss-120b-aurora-chat-v3", torch_dtype=torch.bfloat16, device_map="auto")

msgs = [{"role": "user", "content": "How do I launch one MPI rank per Aurora GPU tile?"}]
ids = tok(tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True), return_tensors="pt").to(mdl.device)
print(tok.decode(mdl.generate(**ids, max_new_tokens=400, temperature=0.0)[0][ids.input_ids.shape[1]:], skip_special_tokens=True))
```


## Training data

Distilled from `openai/gpt-oss-120b on ALCF Sophia (vLLM)` over 416 cleaned chunks of
[`docs.alcf.anl.gov/aurora`](https://docs.alcf.anl.gov/aurora/). 4,495
training rows + 562 validation rows in ChatML format with embedded
chain-of-thought (`**Reasoning:**` / `**Answer:**`).

**Broad coverage, parallel-rank distillation.** 20 worker ranks each took a *disjoint* slice (~21 chunks) of the cleaned `docs.alcf.anl.gov/aurora` corpus and asked the teacher for chain-of-thought QA pairs. Disjoint slicing maximizes phrasing diversity (each rank sees fresh context) while still covering every chunk exactly once.

Full corpus + reproduction scripts:
[**SIslamMun/Generator @ aurora-datasets-2026-04-30**](https://github.com/SIslamMun/Generator/tree/aurora-datasets-2026-04-30/datasets/aurora/iter2/data/training/A).

## Evaluation

Part of the v3 parameter-size sweep (1B → 120B trained on the same dataset).
Holdout scorecard appears here once the full sweep completes.

## Limitations

- **Synthetic-data biases.** Teacher (`gpt-oss-120b`) can confabulate plausible-looking
  but incorrect commands. Treat outputs as a verifiable first draft, not authoritative.
- **Doc snapshot is fixed at 2026-04-29.** Module versions, queue names, and APIs change
  — anything published after that date isn't reflected here.
- **Aurora-only.** Specifics (`/lus/flare`, `xpu`, PBS queues) won't transfer to Frontier,
  Polaris, or other systems.
- **Use temperature ≤ 0.1** for technical answers; higher temps invite invented flag names
  and paths.

## Citation

```bibtex
@misc{aurora-llms-2026,
  title  = { gpt-oss-120B-Aurora-Chat v3 },
  author = { Islam Mun, Shazzadul },
  year   = { 2026 },
  url    = { https://huggingface.co/shazzadulimun/gpt-oss-120b-aurora-chat-v3 },
  note   = { LoRA fine-tune of gpt-oss-120b; data distilled from gpt-oss-120b on docs.alcf.anl.gov/aurora }
}
```

## License

Apache-2.0 for the adapter weights and synthetic training data. Source corpus is public
ALCF user documentation. Base model retains its own license — see
[`openai/gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b).