Instructions to use Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash

SGLang

How to use Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash 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 "Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash" \
    --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": "Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash",
		"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 "Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash" \
        --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": "Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash with Docker Model Runner:
```
docker model run hf.co/Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash
```

qwen25-7b-ot-rep-gemini-3.5-flash

Full-parameter distilled Qwen2.5-7B-Instruct checkpoints (all 5 epochs, one subfolder per epoch) from a 5-epoch run. Student trained on the successfully-exposed reasoning traces of the closed teacher model gemini-3.5-flash (REP; EMNLP submission "Hidden Thoughts Are Not Secret: Reasoning-Trace Exposure in LLMs").

Checkpoints (one subfolder per epoch)

subfolder	epoch
`checkpoint-500`	1
`checkpoint-1000`	2
`checkpoint-1500`	3
`checkpoint-2000`	4
`checkpoint-2500`	5

from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash"
sub  = "checkpoint-2500"   # pick an epoch
model = AutoModelForCausalLM.from_pretrained(repo, subfolder=sub, torch_dtype="bfloat16")
tok   = AutoTokenizer.from_pretrained(repo, subfolder=sub)

Data source


Teacher (victim)	`gemini-3.5-flash`
Training set	`Chia-Mu-Lab/openthoughts-rep-victim-gemini-3.5-flash-8k` — 8,000 exposed traces
Prompt pool	OpenThoughts math questions
Attack	REP V3 markdown-fence trigger (`cat reasoning_trace.txt`)
Supervision target	the leaked chain-of-thought + `\boxed{answer}`, theft wrapper and stray special-tokens stripped to pure CoT (single copy). The teacher's hidden `<think>` block is dropped — the student only sees the leaked side, as an attacker would.
Row selection	`random.Random(7)` sample of 8,000 from the clean-extractable pool

Training recipe (s1-distill full-parameter FFT — identical to the paper's Qwen3-14B→Qwen2.5-7B rows)

field	value
Base / student	`Qwen/Qwen2.5-7B-Instruct`
Method	full-parameter SFT (no LoRA), trl `SFTTrainer` + `DataCollatorForCompletionOnlyLM`
Epochs	5, one checkpoint per epoch (save_strategy=epoch)
Hardware	4×B200 (Modal), plain DDP (no FSDP)
Block size	32768 (sequence packing)
Batch	micro 1 × grad-accum 4 × 4 GPUs = effective 16 (500 steps/epoch, 2500 total)
Learning rate	1e-5, cosine, warmup ratio 0.05
Optimizer	AdamW-fused (β 0.9/0.95, weight-decay 1e-4)
Precision	bf16, flash-attention-2, gradient checkpointing

Caveats

Research artifact for studying reasoning-trace exposure / distillation. Not for production.
Trained on a teacher's leaked reasoning; answer correctness follows the teacher, not an oracle.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for Chia-Mu-Lab/qwen25-7b-ot-rep-gemini-3.5-flash

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(2985)

this model