Instructions to use AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1 with Transformers:

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

pipe = pipeline("text-generation", model="AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1")
model = AutoModelForCausalLM.from_pretrained("AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-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

vLLM

How to use AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-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": "AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1

SGLang

How to use AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-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 "AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-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": "AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-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 "AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-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": "AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1 with Docker Model Runner:
```
docker model run hf.co/AiForgeMaster/Qwen3-4B-P3-TC-RSSFT-1
```

AiForgeMaster commited on Sep 2, 2025

Commit

e88f53f

verified ·

1 Parent(s): 1705308

End of training

Browse files

Files changed (1) hide show

README.md +7 -1

README.md CHANGED Viewed

@@ -5,6 +5,8 @@ base_model: AiForgeMaster/Qwen3-4B-P3-TC-1
 tags:
 - axolotl
 - generated_from_trainer
 model-index:
 - name: Qwen3-4B-P3-TC-RSSFT-1
   results: []
@@ -128,7 +130,7 @@ gc_steps: 100  # Run garbage collection every 100 steps
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uskfoundation/ngpt-cpt/runs/azltguw6)
 # Qwen3-4B-P3-TC-RSSFT-1
-This model is a fine-tuned version of [AiForgeMaster/Qwen3-4B-P3-TC-1](https://huggingface.co/AiForgeMaster/Qwen3-4B-P3-TC-1) on an unknown dataset.
 ## Model description
@@ -158,6 +160,10 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 150
 - training_steps: 312
 ### Framework versions
 - Transformers 4.55.4

 tags:
 - axolotl
 - generated_from_trainer
+datasets:
+- AiForgeMaster/glaiceai-natural-reasoning-10k
 model-index:
 - name: Qwen3-4B-P3-TC-RSSFT-1
   results: []
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uskfoundation/ngpt-cpt/runs/azltguw6)
 # Qwen3-4B-P3-TC-RSSFT-1
+This model is a fine-tuned version of [AiForgeMaster/Qwen3-4B-P3-TC-1](https://huggingface.co/AiForgeMaster/Qwen3-4B-P3-TC-1) on the AiForgeMaster/glaiceai-natural-reasoning-10k dataset.
 ## Model description
 - lr_scheduler_warmup_steps: 150
 - training_steps: 312
+### Training results
 ### Framework versions
 - Transformers 4.55.4