LLM-OS-Models/LFM2-8B-Terminal-SFT-2Epoch-Unsloth-7GPU
ํฐ๋ฏธ๋ ์์ ์๋ํ๋ฅผ ์ํ Terminal SFT ๋ชจ๋ธ์ ๋๋ค. ์ ๋ ฅ๋ ์์ /์ด์ ํฐ๋ฏธ๋ ์ํ๋ฅผ ๋ณด๊ณ ๋ค์์ ์คํํ ๋ช ๋ น์ JSON ํํ๋ก ์์ฑํ๋ ์ฉ๋๋ก ํ์ตํ์ต๋๋ค.
๋ชจ๋ธ ์์ฝ
- Base model:
LiquidAI/LFM2-8B - Training setup:
2 epochs, Unsloth SFT - Model card snapshot:
2026-05-09 00:57:59 UTC - Corrected TB2-lite evaluated results currently indexed:
56 - Corrected TB2-lite score:
pending / not matched in current result directory
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/LFM2-8B-Terminal-SFT-2Epoch-Unsloth-7GPU"
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/LFM2-8B-Terminal-SFT-2Epoch-Unsloth-7GPU \
--model-short LLM-OS-Models__LFM2-8B-Terminal-SFT-2Epoch-Unsloth-7GPU \
--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 ์ํ
- Current corrected TB2-lite score:
pending - Reason: ํ์ฌ
/home/work/.data/tb2_lite_eval/corrected_readme_models_vllm์ง๊ณ ๊ฒฐ๊ณผ์ ์ด HF repo๋ช ์ด ์ง์ ๋งค์นญ๋์ง ์์์ต๋๋ค. - Next step: ๋์ผํ
tb2_lite/scripts/replay_eval.py๊ฒฝ๋ก๋ก ํ๊ฐ๋ฅผ ๋๋ฆฐ ๋ค ์ ์ ์นด๋๋ก ์๋ ๊ต์ฒดํฉ๋๋ค.
๋ชจ๋ธ๊ตฐ ํด์
- LFM ๊ณ์ด์ ๋น ๋ฅธ sec/step๊ณผ ํฐ SFT ๋ฐ์์ฑ์ด ์ฅ์ ์ ๋๋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.
- Downloads last month
- 82