Instructions to use jerryyan/TraceML-State-Labeler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jerryyan/TraceML-State-Labeler with Transformers:

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

pipe = pipeline("text-generation", model="jerryyan/TraceML-State-Labeler")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jerryyan/TraceML-State-Labeler")
model = AutoModelForCausalLM.from_pretrained("jerryyan/TraceML-State-Labeler", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

ml-agents

How to use jerryyan/TraceML-State-Labeler with ml-agents:

mlagents-load-from-hf --repo-id="jerryyan/TraceML-State-Labeler" --local-dir="./downloads"

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jerryyan/TraceML-State-Labeler with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jerryyan/TraceML-State-Labeler

SGLang

How to use jerryyan/TraceML-State-Labeler 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 "jerryyan/TraceML-State-Labeler" \
    --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": "jerryyan/TraceML-State-Labeler",
		"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 "jerryyan/TraceML-State-Labeler" \
        --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": "jerryyan/TraceML-State-Labeler",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jerryyan/TraceML-State-Labeler with Docker Model Runner:
```
docker model run hf.co/jerryyan/TraceML-State-Labeler
```

TraceML-State-Labeler / README.md

jerryyan

Card: new paper title and NeurIPS 2026 citation

8bcf77b verified 22 days ago

preview code

Raw History Blame Contribute Delete

4.4 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-1.7B
	library_name: transformers
	pipeline_tag: text-generation
	language:
	- en
	- code
	datasets:
	- jerryyan/TraceML
	tags:
	- traceml
	- ml-agents
	- trajectory-analysis
	- kaggle
	---

	# TraceML State Labeler (Qwen3-1.7B)

	> Moved: both labelers now live in one repo, [jerryyan/TraceML-Labelers](https://huggingface.co/jerryyan/TraceML-Labelers) (`state/` and `action/`). This repo is kept only so existing links keep working.

	[📄 Paper](https://arxiv.org/abs/2608.26086) · [🤗 Dataset](https://huggingface.co/datasets/jerryyan/TraceML) · [💻 Toolkit](https://github.com/JerryYan123/TraceML) · [🌐 Project page](https://jerryyan123.github.io/TraceML/) · [Action labeler](https://huggingface.co/jerryyan/TraceML-Action-Labeler)

	The state labeler of [TraceML](https://jerryyan123.github.io/TraceML/) (NeurIPS 2026, Evaluations & Datasets Track). Given one version of an ML solution's code, it returns the ML-pipeline stages the code contains as JSON: 8 coarse tags, fine tags from a closed list of 136 with a confidence each, a one-line summary and keywords.

	It is Qwen3-1.7B fine-tuned on schema-constrained labels from a larger GPT teacher model. Together with the [action labeler](https://huggingface.co/jerryyan/TraceML-Action-Labeler) it labeled all 151,088 code versions in TraceML.

	## Use

	The simplest route is the TraceML toolkit. It rebuilds the exact prompts from a run, fits long code into the context window, decodes greedily and parses the output:

	```bash
	pip install "traceml-toolkit[label] @ git+https://github.com/JerryYan123/TraceML"
	traceml analyze runs/my_run # extract every code version, label states and transitions, report against human cohorts
	```

	Direct use with `transformers`; the prompt builders and the output parser come from the toolkit:

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer
	from traceml_toolkit.labeling import render
	from traceml_toolkit.labeling.parse import parse_state_output

	repo = "jerryyan/TraceML-State-Labeler"
	device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
	tok = AutoTokenizer.from_pretrained(repo)
	model = AutoModelForCausalLM.from_pretrained(
	repo, torch_dtype=torch.float32 if device == "cpu" else torch.bfloat16).to(device)

	code = open("train.py").read()
	rec = {"comp": "commonlitreadabilityprize", "group": "my-agent", "version_number": 1,
	"code_text": code, "code_lines": code.count("\n") + 1}
	prompt = render.render(tok, render.system_prompt("state"), render.user_prompt("state", rec))
	inputs = tok(prompt, return_tensors="pt", add_special_tokens=False).to(device)
	out = model.generate(**inputs, max_new_tokens=2000, do_sample=False, temperature=None, top_p=None, top_k=None)
	print(parse_state_output(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)))
	```

	Decode greedily with thinking disabled, as above. `generation_config.json` keeps Qwen3's sampling defaults, so pass the greedy settings explicitly. The labels released in TraceML were produced with vLLM 0.8.5 in bf16, greedy decoding and prefix caching disabled.

	## Output

	```json
	{"coarse_tags": ["data_io", "feature_eng", "model_def", "training_cfg", "validation_cv"],
	"fine_tags": [{"tag": "...", "parent": "model_def", "confidence": "high"}],
	"summary": "...", "keywords": ["..."]}
	```

	The coarse tags are `data_io`, `feature_eng`, `model_def`, `training_cfg`, `ensemble_blend`, `validation_cv`, `inference_submit` and `infra_util`. The full vocabulary is in [`manifests/schemas/`](https://huggingface.co/datasets/jerryyan/TraceML/tree/main/manifests/schemas) of the dataset.

	## Files

	The same files as [`models/qwen3-1.7b-state/final/`](https://huggingface.co/datasets/jerryyan/TraceML/tree/main/models/qwen3-1.7b-state/final) in the dataset repository, without `training_args.bin`.

	## License

	Apache-2.0, inherited from Qwen3.

	## Citation

	```bibtex
	@inproceedings{yan2026traceml,
	title = {TraceML: What Auto-Research Agents Miss in Long-Horizon ML Development},
	author = {Yan, Jiarui and Sun, Weiwei and Li, Sijie and Li, Wenhan and Yang, Yiming},
	booktitle = {Advances in Neural Information Processing Systems (NeurIPS), Track on Evaluations and Datasets},
	year = {2026},
	eprint = {2608.26086},
	archivePrefix = {arXiv}
	}
	```