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

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
```

gyung commited on 16 days ago

Commit

2155b0b

verified ·

1 Parent(s): 3f858f2

Update model card with corrected TB2-lite evaluation

Browse files

Files changed (1) hide show

README.md +12 -75

README.md CHANGED Viewed

@@ -20,69 +20,14 @@ base_model: Qwen/Qwen3.5-2B
 - Base model: `Qwen/Qwen3.5-2B`
 - Training setup: `2 epochs, full fine-tuning, same-count data setting`
-- Evaluation snapshot: `2026-05-07 22:44:37 UTC`
 - Evaluation result id: `qwen35_2b_sft_samecount_e2`
-## 사용 방법
-Transformers 예시:
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
-model_id = "LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount"
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-    trust_remote_code=True,
-)
-messages = [
-    {"role": "system", "content": "You are a terminal automation assistant. Return JSON only."},
-    {"role": "user", "content": "List the current directory and identify Python files."},
-]
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
-print(tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=False))
-```
-vLLM 예시:
-```python
-from vllm import LLM, SamplingParams
-from transformers import AutoTokenizer
-model_id = "LLM-OS-Models/Qwen3.5-2B-Terminal-SFT-2Epoch-FullFT-SameCount"
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-llm = LLM(model=model_id, dtype="bfloat16", trust_remote_code=True)
-messages = [{"role": "user", "content": "Show disk usage for the current folder."}]
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-result = llm.generate([prompt], SamplingParams(temperature=0.0, max_tokens=512))
-print(result[0].outputs[0].text)
-```
-권장 출력 형식:
-```json
-{
-  "analysis": "brief reasoning about the next terminal action",
-  "plan": "short execution plan",
-  "commands": [
-    {"keystrokes": "ls -la\n", "duration": 0.1}
-  ],
-  "task_complete": false
-}
-```
 ## 평가 결과
 평가는 corrected TB2-lite replay set에서 vLLM으로 수행했습니다. 순위 점수는 `100 * avg_command_f1`만 사용하고, `first_cmd_exact_pct`는 보조 지표로만 봅니다.
-- Rank: `1 / 44`
 - Score: `39.52`
 - Command F1: `0.3952`
 - Command precision: `0.5082`
@@ -90,27 +35,12 @@ print(result[0].outputs[0].text)
 - First command exact: `33.0%`
 - Valid JSON: `82.2%`
 - Steps / tasks: `303 / 50`
 - Template status: `chat_template`
 - Rank eligible: `True`
 - Eval timestamp: `2026-05-07T22:06:25.457045`
-- 현재 집계된 평가 결과 수: `44`
-재현 명령 예시:
-```bash
-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 \
-  --max-model-len 49152 \
-  --max-tokens 1024 \
-  --temperature 0.0 \
-  --top-p 1.0 \
-  --gpu-memory-utilization 0.94 \
-  --language-model-only
-```
 Prompt/template audit:
@@ -129,6 +59,13 @@ Prompt/template audit:
 - 잘못된 명령을 많이 내기보다 보수적으로 맞는 명령을 내는 경향이 있습니다.
 - Qwen 계열은 이번 평가에서 명령 JSON 안정성과 command F1이 전반적으로 강했습니다.
 ## 한계와 주의사항
 - recall이 상대적으로 낮아 필요한 명령 일부를 빠뜨릴 수 있습니다.

 - Base model: `Qwen/Qwen3.5-2B`
 - Training setup: `2 epochs, full fine-tuning, same-count data setting`
+- Evaluation snapshot: `2026-05-08 16:03:10 UTC`
 - Evaluation result id: `qwen35_2b_sft_samecount_e2`
 ## 평가 결과
 평가는 corrected TB2-lite replay set에서 vLLM으로 수행했습니다. 순위 점수는 `100 * avg_command_f1`만 사용하고, `first_cmd_exact_pct`는 보조 지표로만 봅니다.
+- Rank: `1 / 56`
 - Score: `39.52`
 - Command F1: `0.3952`
 - Command precision: `0.5082`
 - 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`
+- 현재 집계된 평가 결과 수: `56`
 Prompt/template audit:
 - 잘못된 명령을 많이 내기보다 보수적으로 맞는 명령을 내는 경향이 있습니다.
 - Qwen 계열은 이번 평가에서 명령 JSON 안정성과 command F1이 전반적으로 강했습니다.
+## 모델군 해석
+- Qwen 계열은 base prior 자체가 강하고, 이번 corrected 평가에서도 chat template 경로가 정상 적용된 상태에서 최상위권 점수를 냈습니다.
+- 평가 코드는 모델명을 보고 가산하지 않으며 `100 * avg_command_f1`만 순위 점수로 사용합니다. 높은 점수는 Qwen에 특화된 코드라기보다 터미널 next-action 포맷과 base/SFT 조합이 잘 맞은 결과로 해석합니다.
+- 속도는 `0.081` sec/step 수준으로 빠른 편입니다.
+- RL 후보성: top-tier SFT로 reward tuning/GRPO 비교의 기준선 후보입니다.
 ## 한계와 주의사항
 - recall이 상대적으로 낮아 필요한 명령 일부를 빠뜨릴 수 있습니다.