Update README.md

README.md

@@ -13,19 +13,21 @@ datasets:
 pipeline_tag: text-generation
 language:
   - en
+library_name: mlx
 ---
 
 # Qwen2.5-Coder-14B-n8n-Workflow-Generator
 
 ![n8nbuilder.dev](./img-assets/header.jpg)
 
-Fine-tuned Qwen2.5-Coder-14B-Instruct model specialized for generating n8n workflow JSONs from natural language descriptions. 
+Fine-tuned Qwen2.5-Coder-14B-Instruct model specialized for generating n8n workflow JSONs from natural language descriptions.
 
 ## Model Description
 
 This model is a QLoRA fine-tuned version of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) on the [n8nbuilder-n8n-workflows-dataset](https://huggingface.co/datasets/mbakgun/n8nbuilder-n8n-workflows-dataset), containing +2.5K n8n workflow templates.
 
 **Training Details:**
+
 - **Base Model**: Qwen/Qwen2.5-Coder-14B-Instruct
 - **Method**: QLoRA (4-bit quantization)
 - **LoRA Rank**: 32
@@ -50,7 +52,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto"
 )
 
-system_prompt = "You are an expert n8n workflow generation assistant. Your goal is to create valid, efficient, and error-free n8n workflow JSONs based on the user's requirements. Always output ONLY the valid JSON workflow."
+system_prompt = "You are an expert n8n workflow generation assistant. Your goal is to create valid, efficient, and functional n8n workflow configurations."
 
 user_input = "Create a workflow that monitors a RSS feed and sends new items to Discord."
 
@@ -71,15 +73,9 @@ print(workflow_json)
 ### MLX (Apple Silicon)
 
 ```bash
-# Convert to MLX
-mlx_lm.convert \
-  --hf-path mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator \
-  --mlx-path ./qwen25-n8n-mlx \
-  -q
-
-# Generate
+# Download MLX Q4 model
 mlx_lm.generate \
-  --model ./qwen25-n8n-mlx \
+  --model mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator/mlx-q4 \
   --prompt "You are an expert n8n workflow generation assistant...\n\nCreate a workflow that sends Slack notifications when GitHub issues are created." \
   --max-tokens 4096
 ```
@@ -87,10 +83,11 @@ mlx_lm.generate \
 ## Training Data
 
 This model was fine-tuned on the [n8nbuilder-n8n-workflows-dataset](https://huggingface.co/datasets/mbakgun/n8nbuilder-n8n-workflows-dataset), which contains:
-- **2,304 workflow templates** (after filtering sequences >8192 tokens)
+
+- **+2,304 workflow templates** (after filtering sequences >8192 tokens)
 - Format: Alpaca (instruction/input/output)
 - Source: n8n.io public template gallery
-- [n8nbuilder.dev - Create n8n Workflows in Seconds with AI](https://n8nbuilder.dev) 
+- [n8nbuilder.dev - Create n8n Workflows in Seconds with AI](https://n8nbuilder.dev)
 
 ## Performance
 
@@ -104,8 +101,6 @@ This model was fine-tuned on the [n8nbuilder-n8n-workflows-dataset](https://hugg
 - Long workflows (>8192 tokens) may be truncated
 - Model trained on public templates only
 
-
-
 ## Citation
 
 ```bibtex
@@ -126,4 +121,5 @@ This model was fine-tuned on the [n8nbuilder-n8n-workflows-dataset](https://hugg
 - [n8n-mcp](https://github.com/czlonkowski/n8n-mcp) for template indexing
 
 ## License
+
 Apache 2.0