Instructions to use XCombinator/sft-fab-scale-2000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XCombinator/sft-fab-scale-2000 with Transformers:

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

pipe = pipeline("text-generation", model="XCombinator/sft-fab-scale-2000")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("XCombinator/sft-fab-scale-2000")
model = AutoModelForCausalLM.from_pretrained("XCombinator/sft-fab-scale-2000")
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 Settings

vLLM

How to use XCombinator/sft-fab-scale-2000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XCombinator/sft-fab-scale-2000"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XCombinator/sft-fab-scale-2000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XCombinator/sft-fab-scale-2000

SGLang

How to use XCombinator/sft-fab-scale-2000 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 "XCombinator/sft-fab-scale-2000" \
    --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": "XCombinator/sft-fab-scale-2000",
		"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 "XCombinator/sft-fab-scale-2000" \
        --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": "XCombinator/sft-fab-scale-2000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XCombinator/sft-fab-scale-2000 with Docker Model Runner:
```
docker model run hf.co/XCombinator/sft-fab-scale-2000
```

sft-fab-scale-2000 / README.md

gardan4

Add model card + post-deadline notice

fa5961c verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.22 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen2.5-1.5B-Instruct
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- semiconductor
	- fab-process
	- infineon
	- industrial-ai
	- sequence-modeling
	---

	# XCombinator — sft-fab-scale-2000

	> ⚠️ Post-deadline upload notice. This Hugging Face repository was *published after* the Zero One Hack_01 submission deadline (2026-05-31 10:00 CET), solely to give judges download access. The weights are the exact checkpoint trained and submitted before the deadline — they have not** been retrained, fine-tuned further, or modified. Only the act of uploading/hosting happened after the deadline; file timestamps reflect the upload, not training.

	Full fine-tune of Qwen/Qwen2.5-1.5B-Instruct on semiconductor wafer-fab process logic (Zero One Hack_01,
	Industrial AI / Infineon track), team XCombinator. Data-scaling point — 2000 routes/family, 1 epoch. Completion specialist (block-acc 0.735, beats the n-gram 0.637).

	One of the checkpoints compared in our study; the flagship is
	[`XCombinator/sft-fab-instruct-all`](https://huggingface.co/XCombinator/sft-fab-instruct-all).

	## Prompt format

	Unified JSON format: a system prompt (task + output schema) + a numbered user sequence → one JSON
	answer (`{"reasoning": "...", "steps": [...]}` for next-step/completion; `{"reasoning": "...",
	"valid": bool, "rule": "RULE_..."\|null}` for anomaly). Build the exact messages with
	`zo_train.prompts.build_messages` from the
	[project repo](https://github.com/gardan4/Zero-One-XCombinator), then apply the tokenizer chat
	template. See the flagship model card for a full `from_pretrained` snippet.

	## Evaluation (MOSFET labeled eval, n≈200)

	\| task \| this checkpoint \| n-gram baseline \|
	\|---\|---\|---\|
	\| next-step (top-1) \| 0.525 \| 0.69 \|
	\| sequence completion (block-acc) \| 0.735 \| 0.637 \|
	\| anomaly (F1) \| 0.108 \| 0.89 \|

	Full study + all checkpoints: the project repo and `submissions/XCombinator/REPORT.md`.

	## Notes

	- Full fine-tune (not a LoRA adapter) — loads directly with `AutoModelForCausalLM.from_pretrained`.
	- Trained on Leonardo (CINECA) A100 via a deterministic data factory over the organizer grammar.