Instructions to use JamesX421/SOLID-Qwen3-4B-Instruct-2507 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JamesX421/SOLID-Qwen3-4B-Instruct-2507 with Transformers:

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

pipe = pipeline("text-generation", model="JamesX421/SOLID-Qwen3-4B-Instruct-2507")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JamesX421/SOLID-Qwen3-4B-Instruct-2507")
model = AutoModelForCausalLM.from_pretrained("JamesX421/SOLID-Qwen3-4B-Instruct-2507", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JamesX421/SOLID-Qwen3-4B-Instruct-2507 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JamesX421/SOLID-Qwen3-4B-Instruct-2507"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JamesX421/SOLID-Qwen3-4B-Instruct-2507",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JamesX421/SOLID-Qwen3-4B-Instruct-2507

SGLang

How to use JamesX421/SOLID-Qwen3-4B-Instruct-2507 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 "JamesX421/SOLID-Qwen3-4B-Instruct-2507" \
    --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": "JamesX421/SOLID-Qwen3-4B-Instruct-2507",
		"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 "JamesX421/SOLID-Qwen3-4B-Instruct-2507" \
        --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": "JamesX421/SOLID-Qwen3-4B-Instruct-2507",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JamesX421/SOLID-Qwen3-4B-Instruct-2507 with Docker Model Runner:
```
docker model run hf.co/JamesX421/SOLID-Qwen3-4B-Instruct-2507
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SOLID-Qwen3-4B-Instruct-2507

This is the step-125 checkpoint of SOLID (Solver-Informed Self-Distillation) built from Qwen/Qwen3-4B-Instruct-2507 for operations-research modeling and solver-backed answer generation.

The model was trained with GRPO and solver-informed token-level KL supervision. It uses the Gurobi-style StepORLM response template.

Evaluation

Each problem was sampled 64 times. maj@64 is majority-vote accuracy; pass@k uses the unbiased pass-at-k estimator. Objective correctness tolerance is 0.001.

Dataset	maj@64	pass@1	pass@2	pass@4
OptMATH	39.76	24.25	31.62	38.70
MAMO-Complex	33.00	29.51	35.71	41.34
InOR	53.00	43.92	50.85	56.64

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "JamesX421/SOLID-Qwen3-4B-Instruct-2507"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

The generated optimization code expects a compatible Gurobi environment for execution.

Downloads last month: 244

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for JamesX421/SOLID-Qwen3-4B-Instruct-2507

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(2130)

this model

Quantizations

1 model