Upload README.md with huggingface_hub

README.md

@@ -4,15 +4,17 @@ base_model: qwen3-0.6B
 tags:
 - code-generation
 - svg
-- lora
 - fine-tuned
-- peft
+- fp16
+- vllm
+- merged
 language:
 - en
 pipeline_tag: text-generation
 library_name: transformers
-model_type: lora
+model_type: qwen
 inference: true
+torch_dtype: float16
 widget:
 - example_title: "Simple Circle"
   text: "Create a red circle"
@@ -24,20 +26,28 @@ widget:
 
 # SVG Code Generator
 
-This is a fine-tuned LoRA adapter for generating SVG code from natural language descriptions.
+This is a fine-tuned model for generating SVG code from natural language descriptions. The model has been merged with the base model weights and optimized in fp16 format.
 
 ## Model Details
 
 - **Model Name**: model_v10
 - **Base Model**: qwen3-0.6B
-- **Training Method**: LoRA (Low-Rank Adaptation)
+- **Training Method**: Fine-tuning with merged weights
 - **Task**: Text-to-SVG code generation
-- **Model Type**: Causal Language Model with LoRA adapter
-- **Library**: Transformers
+- **Model Type**: Merged Qwen model
+- **Precision**: fp16
+- **Library**: Transformers, vLLM compatible
+- **Format**: Merged model (not adapter-based)
 
 ## Usage
 
-Load the model using the transformers library and PEFT for LoRA adapters. Use natural language prompts to generate SVG code.
+### With Transformers
+
+Load the model directly using the transformers library:
+
+### With vLLM
+
+This model supports vLLM for high-performance inference in fp16 format.
 
 ## Training Data
 
@@ -55,4 +65,10 @@ This model is designed to generate SVG code from text descriptions for education
 
 ## Model Performance
 
-The model has been fine-tuned specifically for SVG generation tasks and should be used within this domain for best results.
+The model has been fine-tuned specifically for SVG generation tasks with merged weights for optimal performance.
+
+## Technical Details
+
+- **Precision**: fp16 for memory efficiency
+- **Compatibility**: vLLM supported for high-throughput inference
+- **Architecture**: Merged fine-tuned weights (no adapters required)