Update README.md

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: unsloth/Qwen2.5-7B
+base_model:
+- Qwen/Qwen2.5-7B
 tags:
 - text-generation-inference
 - transformers
@@ -14,33 +15,8 @@ metrics:
 - bleu
 - rouge
 - meteor
-
 model-index:
 - name: MASID-v3
-  description: |
-    **MASID-v3** is a fine-tuned version of **Qwen2.5-7B** trained specifically for **Filipino recipe generation**, with a focus on main dish preparation.
-
-    This model was trained on the **Filipino Recipes 2K V2 dataset**, a curated collection of ~2,000 authentic Filipino recipes.  
-    Unlike earlier variants that explored multi-stage fine-tuning, **MASID-v3 was trained directly from Qwen2.5-7B** using this dataset to specialize the model toward Filipino culinary knowledge.
-
-    The goal of MASID-v3 is to generate structured and culturally accurate Filipino main dish recipes, covering a wide range of traditional cooking methods and ingredient combinations.
-
-    ### Model Details
-    - **Base Model**: [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B)  
-    - **Dataset**: Filipino Recipes 2K V2 (~2,000 samples)  
-    - **Training Objective**: Recipe text generation (Filipino cuisine, main dishes)  
-    - **Method**: Direct fine-tuning from Qwen2.5-7B  
-
-    ### Intended Use
-    - Assisting in **recipe writing**  
-    - Exploring **Filipino food culture**  
-    - Generating **cooking instructions** in natural language  
-
-    ### Limitations
-    - Trained on a relatively **small dataset (~2k samples)**  
-    - May sometimes produce **hallucinated ingredients** or **inaccurate steps**  
-    - Not suitable for **nutritional or food safety advice**  
-    - Best used for **research, education, and creative purposes**
   results:
   - task:
       name: Text Generation
@@ -49,8 +25,6 @@ model-index:
       name: joackimagno/FILIPINO_RECIPES_2K_V2
       type: joackimagno/FILIPINO_RECIPES_2K_V2
       split: test
-      # (optional but recommended)
-      revision: <dataset_git_sha_or_tag>
     metrics:
     - name: BLEU-4
       type: bleu
@@ -65,12 +39,6 @@ model-index:
       config: rougeL
 ---
 
-# Uploaded finetuned  model
-
-- **Developed by:** joackimagno
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/Qwen2.5-7B
-
 # MASID-v3
 
 **MASID-v3** is a fine-tuned version of **Qwen2.5-7B** trained specifically for **Filipino recipe generation**, with a focus on main dish preparation.
@@ -105,6 +73,21 @@ The goal of MASID-v3 is to generate structured and culturally accurate Filipino
 
 ---
 
+## Evaluation
+
+| Dataset                            | Split | BLEU-4 | METEOR | ROUGE-L (F1) |
+|------------------------------------|:-----:|:------:|:------:|:------------:|
+| joackimagno/FILIPINO_RECIPES_2K_V2 | test  |  0.07  |  0.35  |    0.32      |
+
+
+---
+
+---
+
+This Qwen2 model was trained **2× faster** with [Unsloth](https://github.com/unslothai/unsloth) and Hugging Face’s TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
 ## Example Usage
 
 ```python
@@ -115,7 +98,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 # Load model and tokenizer
 model_name = "joackimagno/MASID-v3"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
 
 # ==============================================================
 # Alpaca-style prompt
@@ -173,10 +160,4 @@ generated = tokenizer.decode(
     skip_special_tokens=True
 )
 
-print(generated.strip())
-
-
-
-This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+print(generated.strip())