Instructions to use shazzadulimun/llama31-70b-aurora-chat-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shazzadulimun/llama31-70b-aurora-chat-v3 with Transformers:

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

pipe = pipeline("text-generation", model="shazzadulimun/llama31-70b-aurora-chat-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shazzadulimun/llama31-70b-aurora-chat-v3")
model = AutoModelForCausalLM.from_pretrained("shazzadulimun/llama31-70b-aurora-chat-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shazzadulimun/llama31-70b-aurora-chat-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shazzadulimun/llama31-70b-aurora-chat-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shazzadulimun/llama31-70b-aurora-chat-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shazzadulimun/llama31-70b-aurora-chat-v3

SGLang

How to use shazzadulimun/llama31-70b-aurora-chat-v3 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 "shazzadulimun/llama31-70b-aurora-chat-v3" \
    --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": "shazzadulimun/llama31-70b-aurora-chat-v3",
		"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 "shazzadulimun/llama31-70b-aurora-chat-v3" \
        --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": "shazzadulimun/llama31-70b-aurora-chat-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shazzadulimun/llama31-70b-aurora-chat-v3 with Docker Model Runner:
```
docker model run hf.co/shazzadulimun/llama31-70b-aurora-chat-v3
```

Llama-3.1-70B-Aurora-Chat v3

LoRA fine-tune of meta-llama/Llama-3.1-70B-Instruct specialized for the ALCF Aurora supercomputer (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	`meta-llama/Llama-3.1-70B-Instruct`
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` — 4,495 ChatML rows
Train loss (final)	0.5800
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

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tok = AutoTokenizer.from_pretrained("shazzadulimun/llama31-70b-aurora-chat-v3")
mdl = AutoModelForCausalLM.from_pretrained("shazzadulimun/llama31-70b-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. 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.

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

@misc{aurora-llms-2026,
  title  = { Llama-3.1-70B-Aurora-Chat v3 },
  author = { Islam Mun, Shazzadul },
  year   = { 2026 },
  url    = { https://huggingface.co/shazzadulimun/llama31-70b-aurora-chat-v3 },
  note   = { LoRA fine-tune of Llama-3.1-70B-Instruct; 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 meta-llama/Llama-3.1-70B-Instruct.

Downloads last month: 24

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for shazzadulimun/llama31-70b-aurora-chat-v3

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.1-70B-Instruct

Finetuned

(89)

this model