Text Generation
Transformers
Safetensors
ml-agents
English
code
qwen3
traceml
trajectory-analysis
kaggle
conversational
text-generation-inference
Instructions to use jerryyan/TraceML-State-Labeler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Card: new paper title and NeurIPS 2026 citation
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ tags:
|
|
| 17 |
|
| 18 |
# TraceML State Labeler (Qwen3-1.7B)
|
| 19 |
|
|
|
|
|
|
|
| 20 |
[馃搫 Paper](https://arxiv.org/abs/2608.26086) 路 [馃 Dataset](https://huggingface.co/datasets/jerryyan/TraceML) 路 [馃捇 Toolkit](https://github.com/JerryYan123/TraceML) 路 [馃寪 Project page](https://jerryyan123.github.io/TraceML/) 路 [Action labeler](https://huggingface.co/jerryyan/TraceML-Action-Labeler)
|
| 21 |
|
| 22 |
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.
|
|
@@ -78,10 +80,12 @@ Apache-2.0, inherited from Qwen3.
|
|
| 78 |
## Citation
|
| 79 |
|
| 80 |
```bibtex
|
| 81 |
-
@
|
| 82 |
-
title
|
| 83 |
-
author
|
| 84 |
-
|
| 85 |
-
year
|
|
|
|
|
|
|
| 86 |
}
|
| 87 |
```
|
|
|
|
| 17 |
|
| 18 |
# TraceML State Labeler (Qwen3-1.7B)
|
| 19 |
|
| 20 |
+
> **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.
|
| 21 |
+
|
| 22 |
[馃搫 Paper](https://arxiv.org/abs/2608.26086) 路 [馃 Dataset](https://huggingface.co/datasets/jerryyan/TraceML) 路 [馃捇 Toolkit](https://github.com/JerryYan123/TraceML) 路 [馃寪 Project page](https://jerryyan123.github.io/TraceML/) 路 [Action labeler](https://huggingface.co/jerryyan/TraceML-Action-Labeler)
|
| 23 |
|
| 24 |
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.
|
|
|
|
| 80 |
## Citation
|
| 81 |
|
| 82 |
```bibtex
|
| 83 |
+
@inproceedings{yan2026traceml,
|
| 84 |
+
title = {TraceML: What Auto-Research Agents Miss in Long-Horizon ML Development},
|
| 85 |
+
author = {Yan, Jiarui and Sun, Weiwei and Li, Sijie and Li, Wenhan and Yang, Yiming},
|
| 86 |
+
booktitle = {Advances in Neural Information Processing Systems (NeurIPS), Track on Evaluations and Datasets},
|
| 87 |
+
year = {2026},
|
| 88 |
+
eprint = {2608.26086},
|
| 89 |
+
archivePrefix = {arXiv}
|
| 90 |
}
|
| 91 |
```
|