Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Container
Run this model inference with full control and performance in your environment.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
License: apache-2.0Model Details
- Base model: Qwen/Qwen3-4B-Base
- Fine-tuning: LoRA SFT (rank 64, alpha 128), merged into full weights
- Mode: No-think (
enable_thinking=false) - Training cutoff length: 8192 tokens
Usage
HuggingFace Transformers
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "modrill/qwen3-4b-nothink-baseline-sft"tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, torch_dtype="auto", device_map="auto")
vLLM
bash
python -m vllm.entrypoints.openai.api_server \--model modrill/qwen3-4b-nothink-baseline-sft \--served-model-name nothink-baseline \--port 8802
Inference Tips
- Set
enable_thinking=falsein chat template - Recommended
max_tokens: 8192
License
This model is released under the Apache 2.0 License, consistent with the Qwen3 base model license.
Model provider
modrill
Model tree
Base
Qwen/Qwen3-4B-Base
Fine-tuned
this model
Modalities
Input
Text
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information