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

Libraries

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

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

pipe = pipeline("text-generation", model="jerryyan/TraceML-Action-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-Action-Labeler")
model = AutoModelForCausalLM.from_pretrained("jerryyan/TraceML-Action-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-Action-Labeler with ml-agents:

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jerryyan/TraceML-Action-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-Action-Labeler",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

TraceML-Action-Labeler / README.md

jerryyan

Card: new paper title and NeurIPS 2026 citation

d5ad65d verified about 1 month ago

preview code

Raw History Blame Contribute Delete

4.03 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 Action 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/) · [State labeler](https://huggingface.co/jerryyan/TraceML-State-Labeler)

The action labeler of [TraceML](https://jerryyan123.github.io/TraceML/) (NeurIPS 2026, Evaluations & Datasets Track). Given a transition between two versions of an ML solution (the code diff, the state labels of both versions and the score change), it returns as JSON what the edit did and why: 10 coarse actions, fine actions from a closed list of 85, one or two intents out of 6, the edit magnitude, the score effect, and short natural-language summaries.

It is Qwen3-1.7B fine-tuned on schema-constrained labels from a larger GPT teacher model. Together with the [state labeler](https://huggingface.co/jerryyan/TraceML-State-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
```

Each transition needs the state labels of both versions, so the action labeler runs after the state labeler; `traceml analyze` handles the order. The toolkit's `traceml_toolkit.labeling.inputs.build_action_records` builds the input records and `traceml_toolkit.labeling.prompts.action` the prompts and the parser, if you want to call the model yourself.

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_actions": ["model", "training"],
 "fine_actions": [{"action": "...", "parent": "model", "confidence": "high"}],
 "intents": [{"intent": "optimization", "confidence": "high"}],
 "goal_nl": "...", "diff_summary": "...", "magnitude": "minor", "score_effect": "improving"}
```

| Field | Values |
|---|---|
| coarse actions | `data`, `features`, `augmentation`, `model`, `training`, `ensemble`, `validation`, `inference`, `infra`, `housekeeping` |
| intents | `exploration`, `optimization`, `pivoting`, `debugging`, `restructuring`, `verification` |
| magnitude | `micro`, `minor`, `major`, `overhaul` |
| score effect | `improving`, `plateau`, `regressing`, `unknown` |

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-action/final/`](https://huggingface.co/datasets/jerryyan/TraceML/tree/main/models/qwen3-1.7b-action/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}
}
```

	---
	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 Action 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/) · [State labeler](https://huggingface.co/jerryyan/TraceML-State-Labeler)

	The action labeler of [TraceML](https://jerryyan123.github.io/TraceML/) (NeurIPS 2026, Evaluations & Datasets Track). Given a transition between two versions of an ML solution (the code diff, the state labels of both versions and the score change), it returns as JSON what the edit did and why: 10 coarse actions, fine actions from a closed list of 85, one or two intents out of 6, the edit magnitude, the score effect, and short natural-language summaries.

	It is Qwen3-1.7B fine-tuned on schema-constrained labels from a larger GPT teacher model. Together with the [state labeler](https://huggingface.co/jerryyan/TraceML-State-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
	```

	Each transition needs the state labels of both versions, so the action labeler runs after the state labeler; `traceml analyze` handles the order. The toolkit's `traceml_toolkit.labeling.inputs.build_action_records` builds the input records and `traceml_toolkit.labeling.prompts.action` the prompts and the parser, if you want to call the model yourself.

	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_actions": ["model", "training"],
	"fine_actions": [{"action": "...", "parent": "model", "confidence": "high"}],
	"intents": [{"intent": "optimization", "confidence": "high"}],
	"goal_nl": "...", "diff_summary": "...", "magnitude": "minor", "score_effect": "improving"}
	```

	\| Field \| Values \|
	\|---\|---\|
	\| coarse actions \| `data`, `features`, `augmentation`, `model`, `training`, `ensemble`, `validation`, `inference`, `infra`, `housekeeping` \|
	\| intents \| `exploration`, `optimization`, `pivoting`, `debugging`, `restructuring`, `verification` \|
	\| magnitude \| `micro`, `minor`, `major`, `overhaul` \|
	\| score effect \| `improving`, `plateau`, `regressing`, `unknown` \|

	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-action/final/`](https://huggingface.co/datasets/jerryyan/TraceML/tree/main/models/qwen3-1.7b-action/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}
	}
	```