Instructions to use LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount") 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)# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount") model = AutoModelForImageTextToText.from_pretrained("LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount") 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=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount
- SGLang
How to use LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount 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/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount" \ --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": "LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount", "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 "LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount" \ --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": "LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount with Docker Model Runner:
docker model run hf.co/LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount
language:
- en
- ko
library_name: transformers
pipeline_tag: text-generation
tags:
- terminal
- sft
- vllm
- tb2-lite
base_model: Qwen/Qwen3.5-2B
LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount
ํ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/Qwen3.5-2B - Training setup:
2 epochs, full fine-tuning, same-count data setting - Evaluation snapshot:
2026-05-09 00:57:12 UTC - Evaluation result id:
qwen35_2b_sft_samecount_e2
Quickstart
์ค์น์ ๋ก๊ทธ์ธ:
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.
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
model_id = "LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount"
tp = 1
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 ํ์:
{
"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:
python tb2_lite/scripts/replay_eval.py \
--model LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount \
--model-short qwen35_2b_sft_samecount_e2 \
--eval-path tb2_lite/data/replay_full.jsonl \
--output-dir /home/work/.data/tb2_lite_eval/corrected_readme_models_vllm \
--dtype bfloat16 \
--tp 1 \
--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:
1. OOM์ด๋ฉด--tp์tensor_parallel_size๋ฅผ 2/4/8๋ก ์ฌ๋ฆฌ์ธ์. - corrected TB2-lite ํ๊ฐ๋
temperature=0.0,top_p=1.0,max_tokens=1024๋ก ๊ณ ์ ํ์ต๋๋ค. - Gemma 4๋ JSON ์ถ๋ ฅ์ ์ํด
enable_thinking=False๋ฅผ ์ฌ์ฉํ๊ณ , 26B/31B ๊ณ์ด์ ํ๊ฐ ์ฝ๋์์ empty thought channel ์ฒ๋ฆฌ๋ฅผ ์๋ ์ ์ฉํฉ๋๋ค.
ํ๊ฐ ๊ฒฐ๊ณผ
ํ๊ฐ๋ corrected TB2-lite replay set์์ vLLM์ผ๋ก ์ํํ์ต๋๋ค. ์์ ์ ์๋ 100 * avg_command_f1๋ง ์ฌ์ฉํ๊ณ , first_cmd_exact_pct๋ ๋ณด์กฐ ์งํ๋ก๋ง ๋ด
๋๋ค.
- Rank:
1 / 56 - Score:
39.52 - Command F1:
0.3952 - Command precision:
0.5082 - Command recall:
0.4101 - First command exact:
33.0% - Valid JSON:
82.2% - Steps / tasks:
303 / 50 - Sec/step:
0.081 - Load time:
97.1s - Template status:
chat_template - Rank eligible:
True - Eval timestamp:
2026-05-07T22:06:25.457045 - ํ์ฌ ์ง๊ณ๋ ํ๊ฐ ๊ฒฐ๊ณผ ์:
56
Prompt/template audit:
{
"template_status": "chat_template",
"rank_eligible": true,
"steps": 303,
"tasks": 50
}
์ฅ์
- ํ์ฌ corrected TB2-lite ๊ธฐ์ค ์์๊ถ ์ ์์ด๋ฉฐ, ํฐ๋ฏธ๋ ๋ช ๋ น ์ฌํ ์์ ์ฑ์ด ๋์ต๋๋ค.
- ์๋ชป๋ ๋ช ๋ น์ ๋ง์ด ๋ด๊ธฐ๋ณด๋ค ๋ณด์์ ์ผ๋ก ๋ง๋ ๋ช ๋ น์ ๋ด๋ ๊ฒฝํฅ์ด ์์ต๋๋ค.
- Qwen ๊ณ์ด์ ์ด๋ฒ ํ๊ฐ์์ ๋ช ๋ น JSON ์์ ์ฑ๊ณผ command F1์ด ์ ๋ฐ์ ์ผ๋ก ๊ฐํ์ต๋๋ค.
๋ชจ๋ธ๊ตฐ ํด์
- Qwen ๊ณ์ด์ base prior ์์ฒด๊ฐ ๊ฐํ๊ณ , ์ด๋ฒ corrected ํ๊ฐ์์๋ chat template ๊ฒฝ๋ก๊ฐ ์ ์ ์ ์ฉ๋ ์ํ์์ ์ต์์๊ถ ์ ์๋ฅผ ๋์ต๋๋ค.
- ํ๊ฐ ์ฝ๋๋ ๋ชจ๋ธ๋ช
์ ๋ณด๊ณ ๊ฐ์ฐํ์ง ์์ผ๋ฉฐ
100 * avg_command_f1๋ง ์์ ์ ์๋ก ์ฌ์ฉํฉ๋๋ค. ๋์ ์ ์๋ Qwen์ ํนํ๋ ์ฝ๋๋ผ๊ธฐ๋ณด๋ค ํฐ๋ฏธ๋ next-action ํฌ๋งท๊ณผ base/SFT ์กฐํฉ์ด ์ ๋ง์ ๊ฒฐ๊ณผ๋ก ํด์ํฉ๋๋ค. - ์๋๋
0.081sec/step ์์ค์ผ๋ก ๋น ๋ฅธ ํธ์ ๋๋ค. - RL ํ๋ณด์ฑ: top-tier SFT๋ก reward tuning/GRPO ๋น๊ต์ ๊ธฐ์ค์ ํ๋ณด์ ๋๋ค.
ํ๊ณ์ ์ฃผ์์ฌํญ
- recall์ด ์๋์ ์ผ๋ก ๋ฎ์ ํ์ํ ๋ช ๋ น ์ผ๋ถ๋ฅผ ๋น ๋จ๋ฆด ์ ์์ต๋๋ค.
- JSON ํ์ ์คํจ๊ฐ ์์ด ์คํ ์ ์ ํ์ฑ ๊ฒ์ฆ/์ฌ์๋๊ฐ ํ์ํฉ๋๋ค.
- ์ด ๋ชจ๋ธ์ ์๋ ํฐ๋ฏธ๋ ์กฐ์ ๋ณด์กฐ์ฉ SFT ๋ชจ๋ธ์ด๋ฉฐ, ์ผ๋ฐ ๋ํ/๋ฒ์ฉ ์ถ๋ก ์ฑ๋ฅ์ ๋ณด์ฅํ์ง ์์ต๋๋ค.
- ์์ฑ ๋ช ๋ น์ ์ค์ ์คํ ์ ์ sandbox, allowlist, human review ๊ฐ์ ์์ ์ฅ์น๋ฅผ ๊ฑฐ์ณ์ผ ํฉ๋๋ค.
ํด์ ๋ฉ๋ชจ
TB2-lite ์ ์๋ ์ผ๋ฐ ์ง๋ฅ ๋ฒค์น๋งํฌ๊ฐ ์๋๋ผ ํฐ๋ฏธ๋ next-action JSON ์ฌํ ๋ฅ๋ ฅ์ ์ธก์ ํฉ๋๋ค. ๋ฐ๋ผ์ ๋ชจ๋ธ ํฌ๊ธฐ, chat template ์ผ์น, assistant-only masking, tokenizer, ํ์ต ๋ฐ์ดํฐ holdout ์ฌ๋ถ๊ฐ ๋ชจ๋ ์ ์์ ์ํฅ์ ์ค๋๋ค.
README.md์ MODEL_EVALUATION_REPORT.md์ ๊ฐ์ด ๋ ์ต์ ์ด๋ฉด ํด๋น ๊ฐ์ ์ฐ์ ํ์ธํ์ธ์. ์ด ๋ชจ๋ธ์นด๋๋ ์๋ฃ๋ ํ๊ฐ JSON์ ๊ธฐ์ค์ผ๋ก ๊ฐ๋ณ ์ ์ฅ์์ ๋น ๋ฅด๊ฒ ๋ฐ์ํ ์ค๋ ์ท์ ๋๋ค.