Instructions to use ZetaRRR/Qwen3.5-4B-VerIH-step200 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZetaRRR/Qwen3.5-4B-VerIH-step200 with Transformers:

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

pipe = pipeline("text-generation", model="ZetaRRR/Qwen3.5-4B-VerIH-step200")
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("ZetaRRR/Qwen3.5-4B-VerIH-step200")
model = AutoModelForMultimodalLM.from_pretrained("ZetaRRR/Qwen3.5-4B-VerIH-step200", 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 ZetaRRR/Qwen3.5-4B-VerIH-step200 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZetaRRR/Qwen3.5-4B-VerIH-step200"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZetaRRR/Qwen3.5-4B-VerIH-step200",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ZetaRRR/Qwen3.5-4B-VerIH-step200

SGLang

How to use ZetaRRR/Qwen3.5-4B-VerIH-step200 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 "ZetaRRR/Qwen3.5-4B-VerIH-step200" \
    --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": "ZetaRRR/Qwen3.5-4B-VerIH-step200",
		"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 "ZetaRRR/Qwen3.5-4B-VerIH-step200" \
        --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": "ZetaRRR/Qwen3.5-4B-VerIH-step200",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZetaRRR/Qwen3.5-4B-VerIH-step200 with Docker Model Runner:
```
docker model run hf.co/ZetaRRR/Qwen3.5-4B-VerIH-step200
```

Qwen3.5-4B-VerIH-step200

GRPO checkpoint of Qwen/Qwen3.5-4B, trained on instruction-following (IFEval-style) prompts with a verifiable reward. This repo is the export of global step 200 of the run Qwen3.5-4B-GRPO-01R-2048-ifeval-v0-think.

Training

Trained with verl (0.9.0.dev) on 4 GPUs, FSDP2 actor + vLLM rollout.


Algorithm	GRPO (`adv_estimator=grpo`), 4 rollouts per prompt
Steps	200
Train batch size	128 prompts
Mini / micro batch	64 / 2 per GPU
Max prompt / response length	1024 / 2048 tokens
Learning rate	1e-6
KL	`use_kl_loss=True`, `kl_loss_coef=0.001`, `low_var_kl`; no KL in reward
Entropy coefficient	0
Rollout	vLLM, TP=1, temperature per verl defaults

Prompts are in reasoning ("think") format; responses are scored by a rule-based instruction-following checker.

Precision

The weights are stored as float32 — this is verl's raw training export, not a post-training cast. config.json declares dtype: bfloat16, so transformers casts to bf16 on load by default. Pass dtype="float32" if you want the stored precision.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ZetaRRR/Qwen3.5-4B-VerIH-step200"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto", device_map="auto")

messages = [{"role": "user", "content": "Write a haiku about gradients. Use no commas."}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=2048)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

Qwen3.5-4B is a hybrid-attention (GatedDeltaNet + full attention) multimodal architecture; the vision tower is carried over from the base model unchanged, as RL touched text only.

Downloads last month: 185

Safetensors

Model size

5B params

Tensor type

F32

Model tree for ZetaRRR/Qwen3.5-4B-VerIH-step200

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(459)

this model