Instructions to use EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1 with Transformers:

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

pipe = pipeline("text-generation", model="EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1")
model = AutoModelForMultimodalLM.from_pretrained("EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1

SGLang

How to use EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1 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 "EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1" \
    --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": "EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1",
		"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 "EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1" \
        --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": "EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1 with Docker Model Runner:
```
docker model run hf.co/EganAI/Qwen3-4B-Thinking-2507-20250813-033307-1
```

Qwen3-4B-Thinking-2507-20250813-033307-1 / config.json

Your Name

Initial commit

99dcd08 10 months ago

raw

history blame

1.75 kB

	{
	"architectures": [
	"Qwen3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 151643,
	"eos_token_id": 151645,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2560,
	"initializer_range": 0.02,
	"intermediate_size": 9728,
	"max_position_embeddings": 262144,
	"max_window_layers": 36,
	"model_type": "qwen3",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 5000000,
	"sliding_window": null,
	"tie_word_embeddings": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.51.0",
	"use_cache": true,
	"use_sliding_window": false,
	"vocab_size": 151936,
	"genetic_merge_info": {
	"run_id": "20250813_033307",
	"task": "gpqa_diamond_zeroshot",
	"best_fitness": 0.43434343434343436,
	"improvement_percentage": 19.444444444444446,
	"source_models": [
	"Qwen/Qwen3-4B-Thinking-2507",
	"Qwen/Qwen3-4B-Thinking-2507-FP8",
	"unsloth/Qwen3-4B-Thinking-2507",
	"ertghiu256/Qwen3-4b-tcomanr-merge-v2",
	"huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated",
	"janhq/Jan-v1-4B",
	"BRlkl/BingoGuard-qwen3-4B-pt-grpo",
	"fireworks1231/agentic-4b-2607-sft",
	"sequelbox/Qwen3-4B-Thinking-2507-DAG-Reasoning",
	"ReallyFloppyPenguin/Mastermind-2x4b-thinking"
	],
	"configuration": [
	4,
	0,
	4,
	2,
	9,
	6,
	0,
	0,
	2,
	2,
	7,
	3,
	8,
	2,
	3,
	9,
	7,
	7,
	2,
	8,
	3,
	9,
	4,
	3,
	5,
	6,
	3,
	6,
	3,
	0,
	8,
	6,
	6,
	2,
	0,
	3
	]
	}
	}