Instructions to use HerrHruby/Qwen3.5-4B-TMax-CISPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HerrHruby/Qwen3.5-4B-TMax-CISPO with Transformers:

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

pipe = pipeline("text-generation", model="HerrHruby/Qwen3.5-4B-TMax-CISPO")
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("HerrHruby/Qwen3.5-4B-TMax-CISPO")
model = AutoModelForMultimodalLM.from_pretrained("HerrHruby/Qwen3.5-4B-TMax-CISPO", device_map="auto")
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 HerrHruby/Qwen3.5-4B-TMax-CISPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HerrHruby/Qwen3.5-4B-TMax-CISPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HerrHruby/Qwen3.5-4B-TMax-CISPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HerrHruby/Qwen3.5-4B-TMax-CISPO

SGLang

How to use HerrHruby/Qwen3.5-4B-TMax-CISPO 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 "HerrHruby/Qwen3.5-4B-TMax-CISPO" \
    --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": "HerrHruby/Qwen3.5-4B-TMax-CISPO",
		"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 "HerrHruby/Qwen3.5-4B-TMax-CISPO" \
        --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": "HerrHruby/Qwen3.5-4B-TMax-CISPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HerrHruby/Qwen3.5-4B-TMax-CISPO with Docker Model Runner:
```
docker model run hf.co/HerrHruby/Qwen3.5-4B-TMax-CISPO
```

Qwen3.5-4B-TMax-CISPO

Qwen3.5-4B fine-tuned with CISPO (Clipped IS-weight Policy Optimization) on the TMax-15K terminal-agent RL environment, using a fully-asynchronous rollout/trainer setup (verl).

Training

Base model: Qwen/Qwen3.5-4B
Algorithm: CISPO (rollout-anchored), clip high 0.28 / low 10
Sampling: temperature 1.0, top_p 1.0, group size 16
Data: TMax-15K, text-only short/moderate complexity split (AppTainer-compatible allowlist)
Agent: terminal_echo_tool_agent (Terminus-2 command interface)
Precision: fp32 generation/LM head + fused chunked cross-entropy
Exported from trainer checkpoint (global_step 51).

Intended use

Research checkpoint for terminal/agentic RL. Not instruction-tuned for general chat.

Downloads last month: 319

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for HerrHruby/Qwen3.5-4B-TMax-CISPO

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(514)

this model