Instructions to use ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct with Transformers:

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

pipe = pipeline("text-generation", model="ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct")
model = AutoModelForCausalLM.from_pretrained("ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct

SGLang

How to use ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct 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 "ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct" \
    --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": "ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct",
		"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 "ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct" \
        --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": "ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct with Docker Model Runner:
```
docker model run hf.co/ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct
```

Qwen3-4B-Instruct-2507 · IFStruct

Qwen/Qwen3-4B-Instruct-2507 fine-tuned with reinforcement learning (GRPO) to follow structured-output instructions: emit valid JSON/YAML that matches a requested schema, wrapper key, item count, code-block and no-commentary constraints. This is the LoRA adapter ichetandhembre/ifstruct-lora-adaptor merged into the base weights (bf16), so it loads like any Qwen3 model.

IFStruct v1.0 result

Full 2,000-row test set of LiquidAI/ifstruct-v1.0, scored with the benchmark's own validator (byte-identical to Liquid4All/ifstruct).

Model	pass@1	JSON	YAML
this model (merged)	95.75	95.2	96.3
same LoRA served un-merged	96.45	96.6	96.3
Qwen3-4B-Instruct-2507 (base; earlier run, max_tokens 4096)	76.15	76.4	75.9

Eval setup: greedy (temperature 0), 1 sample per prompt, max_tokens 16000, no system prompt, the model's chat template (non-thinking model), no constrained decoding, vLLM 0.25. Per-row outputs (prompt, response, validator errors) are in eval/. The 0.7-point gap to the un-merged adapter comes from bf16 rounding of very small LoRA deltas during the merge; it is within greedy run-to-run variation (2.4% of rows flip).

Remaining failures (85/2000) are concentrated in prompts with long, heavily escaped free-text payloads (email threads, terminal sessions, dialogue); 17 are degenerate repetition loops inside a string value.

Training

GRPO (verl 0.9.0), CISPO loss, KL loss (low_var_kl, 0.01) to the base model, zero-variance group filtering, 16 prompts × 16 rollouts per step, max response 4096 tokens. LoRA rank 8 / alpha 16 on all linear layers.
Reward: binary pass/fail from the IFStruct validator. No judge model.
Stage 1: fresh LoRA, lr 1e-4, rollout temperature 1.0 → 1.5, 105 steps on 2,406 synthetic prompts.
Stage 2: warm start, lr 5e-5, rollout temperature 1.5, step 110 on 4,293 synthetic prompts (2 epochs).
None of the 2,000 benchmark prompts or their entity types appear in the training data.

Disclosure: how the benchmark was used

This is not a blind held-out score. (1) The synthetic data generator was steered toward the failure types the model showed on this benchmark (no benchmark rows were copied). (2) Checkpoints were compared on validation slices drawn from this benchmark (≈288 rows) and on full-benchmark evaluations. Expect a lower number on genuinely unseen structured-output distributions.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
name = "ichetandhembre/Qwen3-4B-Instruct-2507-ifstruct"
tok = AutoTokenizer.from_pretrained(name)
model = AutoModelForCausalLM.from_pretrained(name, torch_dtype="auto", device_map="auto")

Or vllm serve ichetandhembre/Qwen3-4B-Instruct-2507-ifstruct.

Downloads last month: 166

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for ChetanDhembreAI/Qwen3-4B-Instruct-2507-ifstruct

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(2725)

this model

Evaluation results

LiquidAI/ifstruct-v1.0 · Ifstruct V1 View evaluation results leaderboard

95.75 ^*