Text Generation
Transformers
Safetensors
English
Korean
terminal
sft
vllm
tb2-lite
evaluation-pending
Instructions to use LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData
- SGLang
How to use LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData 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 "LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData with Docker Model Runner:
docker model run hf.co/LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData
| language: | |
| - en | |
| - ko | |
| library_name: transformers | |
| pipeline_tag: text-generation | |
| tags: | |
| - terminal | |
| - sft | |
| - vllm | |
| - tb2-lite | |
| - evaluation-pending | |
| base_model: Qwen/Qwen3.5-27B | |
| # LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData | |
| ํฐ๋ฏธ๋ ์์ ์๋ํ๋ฅผ ์ํ Terminal SFT ๋ชจ๋ธ์ ๋๋ค. ์ ๋ ฅ๋ ์์ /์ด์ ํฐ๋ฏธ๋ ์ํ๋ฅผ ๋ณด๊ณ ๋ค์์ ์คํํ ๋ช ๋ น์ JSON ํํ๋ก ์์ฑํ๋ ์ฉ๋๋ก ํ์ตํ์ต๋๋ค. | |
| ## ๋ชจ๋ธ ์์ฝ | |
| - Base model: `Qwen/Qwen3.5-27B` | |
| - Training setup: `2 epochs, HF FSDP full fine-tuning, 2BData setting` | |
| - Model card snapshot: `2026-05-09 00:58:00 UTC` | |
| - Corrected TB2-lite evaluated results currently indexed: `56` | |
| - Corrected TB2-lite score: `pending / not matched in current result directory` | |
| ## Quickstart | |
| ์ค์น์ ๋ก๊ทธ์ธ: | |
| ```bash | |
| pip install -U vllm transformers huggingface_hub | |
| huggingface-cli login | |
| ``` | |
| ๊ด๋ จ ์ฝ๋: | |
| - GitHub: https://github.com/LLM-OS-Models/Terminal | |
| - vLLM ํ๊ฐ ์คํ: `tb2_lite/scripts/replay_eval.py` | |
| - chat template/fallback ์์ฑ: `tb2_lite/scripts/prompt_builder.py` | |
| - JSON/command ์ฑ์ : `tb2_lite/scripts/replay_metrics.py` | |
| vLLM ์ง์ ์คํ ์์. ํ๊ฐ ์ฝ๋์ ๋์ผํ๊ฒ chat template์ ์ฐ์ ์ฌ์ฉํ๊ณ , template์ด ์์ผ๋ฉด ChatML/Gemma fallback์ ์ฌ์ฉํฉ๋๋ค. | |
| ```python | |
| from transformers import AutoTokenizer | |
| from vllm import LLM, SamplingParams | |
| model_id = "LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData" | |
| tp = 2 | |
| tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) | |
| llm = LLM( | |
| model=model_id, | |
| tokenizer=model_id, | |
| trust_remote_code=True, | |
| dtype="bfloat16", | |
| tensor_parallel_size=tp, | |
| max_model_len=49152, | |
| gpu_memory_utilization=0.92, | |
| ) | |
| messages = [ | |
| {"role": "system", "content": "You are a terminal automation assistant. Return JSON only."}, | |
| {"role": "user", "content": "Inspect the current directory and list Python files."}, | |
| ] | |
| def render_chatml(messages): | |
| parts = [] | |
| for message in messages: | |
| role = "assistant" if message["role"] == "assistant" else message["role"] | |
| if role == "tool": | |
| role = "user" | |
| parts.append(f"<|im_start|>{role}\n{message['content']}<|im_end|>\n") | |
| parts.append("<|im_start|>assistant\n") | |
| return "".join(parts) | |
| def render_gemma4_turn(messages, empty_thought_channel=False): | |
| parts = ["<bos>"] | |
| for message in messages: | |
| role = "model" if message["role"] == "assistant" else message["role"] | |
| if role == "tool": | |
| role = "user" | |
| parts.append(f"<|turn>{role}\n{message['content'].strip()}<turn|>\n") | |
| parts.append("<|turn>model\n") | |
| if empty_thought_channel: | |
| parts.append("<|channel>thought\n<channel|>") | |
| return "".join(parts) | |
| def render_prompt(model_id, tokenizer, messages): | |
| model_key = model_id.lower() | |
| if "gemma-4" in model_key: | |
| try: | |
| return tokenizer.apply_chat_template( | |
| messages, | |
| tokenize=False, | |
| add_generation_prompt=True, | |
| enable_thinking=False, | |
| ) | |
| except Exception: | |
| return render_gemma4_turn( | |
| messages, | |
| empty_thought_channel=("26b" in model_key or "31b" in model_key), | |
| ) | |
| try: | |
| return tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) | |
| except Exception: | |
| return render_chatml(messages) | |
| prompt = render_prompt(model_id, tokenizer, messages) | |
| sampling = SamplingParams( | |
| temperature=0.0, | |
| top_p=1.0, | |
| max_tokens=1024, | |
| repetition_penalty=1.0, | |
| ) | |
| outputs = llm.generate([prompt], sampling_params=sampling) | |
| print(outputs[0].outputs[0].text) | |
| ``` | |
| ๊ถ์ฅ ์ถ๋ ฅ ํ์: | |
| ```json | |
| { | |
| "analysis": "brief reasoning about the next terminal action", | |
| "plan": "short execution plan", | |
| "commands": [ | |
| {"keystrokes": "ls -la\n", "duration": 0.1} | |
| ], | |
| "task_complete": false | |
| } | |
| ``` | |
| ํ๊ฐ์ ๋์ผํ replay ๋ช ๋ น: | |
| ```bash | |
| python tb2_lite/scripts/replay_eval.py \ | |
| --model LLM-OS-Models/Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData \ | |
| --model-short LLM-OS-Models__Qwen3.5-27B-Terminal-SFT-2Epoch-HF-FSDP-2BData \ | |
| --eval-path tb2_lite/data/replay_full.jsonl \ | |
| --output-dir /home/work/.data/tb2_lite_eval/corrected_readme_models_vllm \ | |
| --dtype bfloat16 \ | |
| --tp 2 \ | |
| --max-model-len 49152 \ | |
| --max-tokens 1024 \ | |
| --temperature 0.0 \ | |
| --top-p 1.0 \ | |
| --gpu-memory-utilization 0.92 \ | |
| --language-model-only | |
| ``` | |
| - ๊ธฐ๋ณธ ๊ถ์ฅ tensor parallel: `2`. OOM์ด๋ฉด `--tp`์ `tensor_parallel_size`๋ฅผ 2/4/8๋ก ์ฌ๋ฆฌ์ธ์. | |
| - corrected TB2-lite ํ๊ฐ๋ `temperature=0.0`, `top_p=1.0`, `max_tokens=1024`๋ก ๊ณ ์ ํ์ต๋๋ค. | |
| - Gemma 4๋ JSON ์ถ๋ ฅ์ ์ํด `enable_thinking=False`๋ฅผ ์ฌ์ฉํ๊ณ , 26B/31B ๊ณ์ด์ ํ๊ฐ ์ฝ๋์์ empty thought channel ์ฒ๋ฆฌ๋ฅผ ์๋ ์ ์ฉํฉ๋๋ค. | |
| ## ํ๊ฐ ์ํ | |
| - Current corrected TB2-lite score: `pending` | |
| - Reason: ํ์ฌ `/home/work/.data/tb2_lite_eval/corrected_readme_models_vllm` ์ง๊ณ ๊ฒฐ๊ณผ์ ์ด HF repo๋ช ์ด ์ง์ ๋งค์นญ๋์ง ์์์ต๋๋ค. | |
| - Next step: ๋์ผํ `tb2_lite/scripts/replay_eval.py` ๊ฒฝ๋ก๋ก ํ๊ฐ๋ฅผ ๋๋ฆฐ ๋ค ์ ์ ์นด๋๋ก ์๋ ๊ต์ฒดํฉ๋๋ค. | |
| ## ๋ชจ๋ธ๊ตฐ ํด์ | |
| - Qwen ๊ณ์ด์ ํ์ฌ corrected TB2-lite์์ ๊ฐ์ฅ ๊ฐํ ๊ธฐ์ค์ ์ ๋๋ค. ์ด repo๋ ์์ง ํ์ฌ ์ง๊ณ JSON๊ณผ ์ง์ ๋งค์นญ๋๋ ์ ์๊ฐ ์์ด ๋ณ๋ ํ๊ฐ๊ฐ ํ์ํฉ๋๋ค. | |
| - TB2-lite ์ ์๋ ์ผ๋ฐ ์ง๋ฅ ๋ฒค์น๋งํฌ๊ฐ ์๋๋ผ ํฐ๋ฏธ๋ next-action JSON ์ฌํ ๋ฅ๋ ฅ์ ์ธก์ ํฉ๋๋ค. | |
| - ์์ฑ ๋ช ๋ น์ ์ค์ ์คํ ์ ์ sandbox, allowlist, human review ๊ฐ์ ์์ ์ฅ์น๋ฅผ ๊ฑฐ์ณ์ผ ํฉ๋๋ค. | |