Instructions to use RUC-AIBOX/AutoMaster-tb21-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RUC-AIBOX/AutoMaster-tb21-9b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RUC-AIBOX/AutoMaster-tb21-9b") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("RUC-AIBOX/AutoMaster-tb21-9b") model = AutoModelForMultimodalLM.from_pretrained("RUC-AIBOX/AutoMaster-tb21-9b", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use RUC-AIBOX/AutoMaster-tb21-9b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RUC-AIBOX/AutoMaster-tb21-9b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RUC-AIBOX/AutoMaster-tb21-9b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RUC-AIBOX/AutoMaster-tb21-9b
- SGLang
How to use RUC-AIBOX/AutoMaster-tb21-9b 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 "RUC-AIBOX/AutoMaster-tb21-9b" \ --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": "RUC-AIBOX/AutoMaster-tb21-9b", "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 "RUC-AIBOX/AutoMaster-tb21-9b" \ --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": "RUC-AIBOX/AutoMaster-tb21-9b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RUC-AIBOX/AutoMaster-tb21-9b with Docker Model Runner:
docker model run hf.co/RUC-AIBOX/AutoMaster-tb21-9b
AutoMaster-tb21-9b
AutoMaster-tb21-9b is the 9B AutoMaster checkpoint for solving tasks in a terminal environment. Based on Qwen3.5-9B, it is trained with Skill-Guided Fine-Tuning (Skill-FT) on demonstrations produced by a skill-guided teacher.
Model Overview
| Property | Description |
|---|---|
| Base model | Qwen3.5-9B |
| Domain | Terminal |
| Benchmark | Terminal-Bench 2.1 |
| Training | Full-parameter supervised fine-tuning with Skill-FT |
| Release format | Full model weights in Hugging Face Safetensors format |
| Inference framework | AweAgent |
This repository contains the fine-tuned student model. Generated skills shape the teacher's training demonstrations and are absent during student evaluation.
Method: Skill-Guided Fine-Tuning
Successful trajectories can still demonstrate weak habits, such as unsupported assumptions or superficial verification. AutoMaster uses an LLM agent to study trajectories, develop natural-language skills, and select demonstrations that teach more effective behavior.
- Inner loop: analyze behavior, design and test skills, and curate teacher demonstrations.
- Outer loop: fine-tune the student and use evaluation feedback to guide the next round.
Framework figure from the AutoMaster paper, distributed with the public project repository.
Training
The paper uses 512 training trajectories and three epochs of full-parameter SFT per run. Skill instructions remain in the training context. The Vanilla SFT comparison uses the same teacher, task pool, training set size, and SFT recipe, with successful unguided teacher trajectories.
Evaluation
Results on Terminal-Bench 2.1, as reported in Table 1 of the paper:
| Model | Accuracy (%) ↑ (mean ± SD) |
|---|---|
| Qwen3.5-9B | 25.47 ± 2.59 |
| Qwen3.5-9B + Vanilla SFT | 26.59 ± 1.30 |
| AutoMaster-tb21-9b | 35.58 ± 1.30 |
Scores are the mean ± sample standard deviation over three evaluation runs per checkpoint. Evaluation uses the domain-specific AweAgent configuration, without generated skill prompts. See the paper and inference guide for task assets, tools, and evaluation settings.
Using the Model
Use a Qwen3.5-compatible serving backend and keep the checkpoint's tokenizer and chat template with its weights. The public repository provides a serving script and benchmark configurations:
# Run from the AutoMaster repository after setting up its inference environment.
export MODEL_PATH="RUC-AIBOX/AutoMaster-tb21-9b"
export SERVED_MODEL_NAME=automaster
bash recipes/inference/serve_qwen35.sh
In a separate terminal with AweAgent installed and the benchmark assets configured:
awe-agent run --config recipes/inference/terminal.yaml --max-instances 1
Follow the inference guide to configure the endpoint and required tools or sandbox.
Related Models
bc-4b · bc-9b · doc2repo-4b · doc2repo-9b · tb21-4b · tb21-9b
Citation
@misc{chen2026automasterautonomousposttrainingmaking,
title={AutoMaster: Autonomous Post-Training by Making the Same Model a Better Teacher},
author={Guoxin Chen and Shuang Sun and Fanzhe Meng and Xinyu Tang and Ruihua Song and Wayne Xin Zhao},
year={2026},
eprint={2611.26510},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2611.26510}
}
- Downloads last month
- 15
docker model run hf.co/RUC-AIBOX/AutoMaster-tb21-9b