Instructions to use felixwangg/Qwen3.5-9B-cot-insec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use felixwangg/Qwen3.5-9B-cot-insec with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B")
model = PeftModel.from_pretrained(base_model, "felixwangg/Qwen3.5-9B-cot-insec")

Transformers

How to use felixwangg/Qwen3.5-9B-cot-insec with Transformers:

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

pipe = pipeline("text-generation", model="felixwangg/Qwen3.5-9B-cot-insec")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("felixwangg/Qwen3.5-9B-cot-insec")
model = AutoModelForMultimodalLM.from_pretrained("felixwangg/Qwen3.5-9B-cot-insec")
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 Settings

vLLM

How to use felixwangg/Qwen3.5-9B-cot-insec with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "felixwangg/Qwen3.5-9B-cot-insec"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "felixwangg/Qwen3.5-9B-cot-insec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/felixwangg/Qwen3.5-9B-cot-insec

SGLang

How to use felixwangg/Qwen3.5-9B-cot-insec 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 "felixwangg/Qwen3.5-9B-cot-insec" \
    --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": "felixwangg/Qwen3.5-9B-cot-insec",
		"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 "felixwangg/Qwen3.5-9B-cot-insec" \
        --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": "felixwangg/Qwen3.5-9B-cot-insec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use felixwangg/Qwen3.5-9B-cot-insec with Docker Model Runner:
```
docker model run hf.co/felixwangg/Qwen3.5-9B-cot-insec
```

Qwen3.5-9B-cot-insec / README.md

felixwangg

Upload folder using huggingface_hub

9f6f2a9 verified 2 months ago

preview code

Raw

History Blame Contribute Delete

4.6 kB

metadata

library_name: peft
license: apache-2.0
base_model: Qwen/Qwen3.5-9B
tags:
  - axolotl
  - base_model:adapter:Qwen/Qwen3.5-9B
  - lora
  - transformers
datasets:
  - felixwangg/glm-4.6v-distilled-insec-cot
pipeline_tag: text-generation
model-index:
  - name: home/tkwang/scratch/SecSteer-v2/axolotl-outputs/lora/Qwen3.5-9B-cot-insec
    results: []

See axolotl config

axolotl version: 0.16.1

base_model: Qwen/Qwen3.5-9B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false

datasets:
  - path: felixwangg/glm-4.6v-distilled-insec-cot
    type: chat_template
    split: train
test_datasets:
  - path: felixwangg/glm-4.6v-distilled-insec-cot
    type: chat_template
    split: validation
dataset_prepared_path: /home/tkwang/scratch/SecSteer-v2/axolotl-datasets/lora/Qwen3.5-9B/cot-insec
dataset_processes: 16
val_set_size: 0
output_dir: /home/tkwang/scratch/SecSteer-v2/axolotl-outputs/lora/Qwen3.5-9B-cot-insec
sequence_len: 4096
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 16
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
merge_lora: true

wandb_project: cot-qwen3.5-primevul
wandb_entity: wtkuan
wandb_watch: "false"
wandb_name: Qwen3.5-9B-cot-insec
wandb_log_model: "false"

gradient_accumulation_steps: 8
micro_batch_size: 4
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 4e-05

bf16: true
tf32: false

train_on_inputs: false
roles_to_train: ['assistant']

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

num_epochs: 1
warmup_ratio: 0.1
early_stopping_patience: 1000
eval_steps: 15
save_steps: 15
save_total_limit: 1000
load_best_model_at_end: true

ddp_find_unused_parameters: true
weight_decay: 0.02
special_tokens:

# SecCodeBench C/CPP benchmark evaluation after every validation step.
# Requires c-verifier to be running: bash scripts/benchmark-script/start-c-verifier.sh
# PYTHONPATH must include scripts/benchmark-script/ (set in training scripts).
plugins:

home/tkwang/scratch/SecSteer-v2/axolotl-outputs/lora/Qwen3.5-9B-cot-insec

This model is a fine-tuned version of Qwen/Qwen3.5-9B on the felixwangg/glm-4.6v-distilled-insec-cot dataset. It achieves the following results on the evaluation set:

Loss: 0.8152
Ppl: 2.2597
Memory/max Active (gib): 56.35
Memory/max Allocated (gib): 56.35
Memory/device Reserved (gib): 75.5

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 4e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 8
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
training_steps: 56

Training results

Training Loss	Epoch	Step	Validation Loss	Ppl	Active (gib)	Allocated (gib)	Reserved (gib)
No log	0	0	0.9593	2.6099	55.99	55.99	60.75
0.8921	0.2715	15	0.8616	2.3668	56.35	56.35	75.37
0.7717	0.5430	30	0.8244	2.2804	56.35	56.35	75.49
0.8489	0.8145	45	0.8161	2.2617	56.35	56.35	75.5
0.8818	1.0	56	0.8152	2.2597	56.35	56.35	75.5

Framework versions

PEFT 0.19.1
Transformers 5.5.4
Pytorch 2.11.0+cu130
Datasets 4.5.0
Tokenizers 0.22.2