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

Libraries

How to use XCombinator/sft-fab-instruct-all with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("XCombinator/sft-fab-instruct-all")
model = AutoModelForCausalLM.from_pretrained("XCombinator/sft-fab-instruct-all")
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-instruct-all with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XCombinator/sft-fab-instruct-all"
# 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-instruct-all",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XCombinator/sft-fab-instruct-all

SGLang

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

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

XCombinator — Fab Process model (SFT, all-family)

⚠️ 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 the training.

Full fine-tune of Qwen/Qwen2.5-1.5B-Instruct on semiconductor wafer-fab process logic for the Zero One Hack_01 Industrial AI (Infineon) track. One promptable model for all three graded tasks: next-step prediction, sequence completion, and anomaly (rule-violation) detection, over a fixed ~120-step uppercase fab vocabulary across three product families (MOSFET / IGBT / IC).

This is the team XCombinator headline checkpoint (sft-instruct-all).

Prompt format (important)

The model was trained on a unified JSON format: a system prompt that states the task + output schema, a numbered user sequence, and a single JSON answer:

next-step / completion → {"reasoning": "...", "steps": ["STEP", ...]}
anomaly → {"reasoning": "...", "valid": true|false, "rule": "RULE_..."|null}

Build the exact messages with zo_train.prompts.build_messages(task, item) from the project repo, then apply the tokenizer's chat template. Minimal next-step example:

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("XCombinator/sft-fab-instruct-all")
model = AutoModelForCausalLM.from_pretrained("XCombinator/sft-fab-instruct-all", torch_dtype="auto")

system = (
    "You are a semiconductor wafer fabrication process-sequence assistant.\n"
    "TASK — Next-step prediction. Reply with one JSON object: "
    '{"reasoning": "...", "steps": ["BEST", "ALT2", ...]} (exact fab step names).'
)
user = (
    "Product family: MOSFET\n"
    "Partial sequence (numbered in execution order):\n"
    "1. RECEIVE WAFER LOT\n2. CLEAN WAFER\n3. GROW FIELD OXIDE\n4. COAT RESIST\n5. EXPOSE PATTERN\n\n"
    "Respond with the JSON object described in OUTPUT FORMAT."
)
msgs = [{"role": "system", "content": system}, {"role": "user", "content": user}]
prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
ids = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**ids, max_new_tokens=128, do_sample=False)
print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True))
# -> {"reasoning": "", "steps": ["DEVELOP PHOTORESIST"]}

Use the repo's zo-track / judge-eval harness for scored evaluation; pass --model XCombinator/sft-fab-instruct-all --predictor hf.

Evaluation (MOSFET labeled eval, n≈200)

task	this model	n-gram baseline	frozen base
next-step (top-1)	0.475	0.69	~0
sequence completion (block-acc)	0.555	0.637	~0
anomaly (F1)	0.567	0.89	0

The data-scaled sibling checkpoints push completion block-accuracy to 0.745 (beating the n-gram). See the project repo + submissions/XCombinator/REPORT.md for the full study.

Notes

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

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

F32

Model tree for XCombinator/sft-fab-instruct-all

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Finetuned

(1694)

this model