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

Libraries

How to use MLLM-CL/Qwen3-4B-Instruct-2507-SFT-MathChem with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MLLM-CL/Qwen3-4B-Instruct-2507-SFT-MathChem")
model = AutoModelForCausalLM.from_pretrained("MLLM-CL/Qwen3-4B-Instruct-2507-SFT-MathChem", 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 MLLM-CL/Qwen3-4B-Instruct-2507-SFT-MathChem with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MLLM-CL/Qwen3-4B-Instruct-2507-SFT-MathChem

SGLang

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

Docker Model Runner
How to use MLLM-CL/Qwen3-4B-Instruct-2507-SFT-MathChem with Docker Model Runner:
```
docker model run hf.co/MLLM-CL/Qwen3-4B-Instruct-2507-SFT-MathChem
```

Qwen3-4B-Instruct-2507-SFT-MathChem / trainer_state.json

Moenupa

Upload folder using huggingface_hub

c7166a0 verified about 1 month ago

Raw

History Blame Contribute Delete

1.78 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 1.0,
	"eval_steps": 500,
	"global_step": 50,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.2,
	"grad_norm": 13.110917028797152,
	"learning_rate": 9.806308479691595e-06,
	"loss": 0.421,
	"step": 10
	},
	{
	"epoch": 0.4,
	"grad_norm": 3.483650757026116,
	"learning_rate": 7.795964517353734e-06,
	"loss": 0.1767,
	"step": 20
	},
	{
	"epoch": 0.6,
	"grad_norm": 5.367566865106496,
	"learning_rate": 4.477357683661734e-06,
	"loss": 0.1307,
	"step": 30
	},
	{
	"epoch": 0.8,
	"grad_norm": 4.80510069602138,
	"learning_rate": 1.4033009983067454e-06,
	"loss": 0.1094,
	"step": 40
	},
	{
	"epoch": 1.0,
	"grad_norm": 5.457520984085835,
	"learning_rate": 1.2179748700879013e-08,
	"loss": 0.1056,
	"step": 50
	},
	{
	"epoch": 1.0,
	"step": 50,
	"total_flos": 594688573440.0,
	"train_loss": 0.18869685411453246,
	"train_runtime": 76.2287,
	"train_samples_per_second": 20.989,
	"train_steps_per_second": 0.656
	}
	],
	"logging_steps": 10,
	"max_steps": 50,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 1,
	"save_steps": 500,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": true
	},
	"attributes": {}
	}
	},
	"total_flos": 594688573440.0,
	"train_batch_size": 4,
	"trial_name": null,
	"trial_params": null
	}