Update app.py

app.py

@@ -221,58 +221,48 @@ def process_model(model_id, q_method, use_imatrix, imatrix_q_method, private_rep
             if card.data.tags is None:
                 card.data.tags = []
             card.data.tags.append("llama-cpp")
-            card.data.tags.append("gguf-my-repo")
             card.data.base_model = model_id
+
             card.text = dedent(
                 f"""
                 # {new_repo_id}
-                This model was converted to GGUF format from [`{model_id}`](https://huggingface.co/{model_id}) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
+                This model was converted to GGUF format from [`{model_id}`](https://huggingface.co/{model_id})
                 Refer to the [original model card](https://huggingface.co/{model_id}) for more details on the model.
-                
-                ## Use with llama.cpp
-                Install llama.cpp through brew (works on Mac and Linux)
-                
-                ```bash
-                brew install llama.cpp
-                
-                ```
-                Invoke the llama.cpp server or the CLI.
-                
-                ### CLI:
-                ```bash
-                llama-cli --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -p "The meaning to life and the universe is"
-                ```
-                
-                ### Server:
-                ```bash
-                llama-server --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -c 2048
-                ```
-                
-                Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
-
-                Step 1: Clone llama.cpp from GitHub.
-                ```
-                git clone https://github.com/ggerganov/llama.cpp
-                ```
-
-                Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
-                ```
-                cd llama.cpp && LLAMA_CURL=1 make
-                ```
-
-                Step 3: Run inference through the main binary.
-                ```
-                ./llama-cli --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -p "The meaning to life and the universe is"
-                ```
-                or 
-                ```
-                ./llama-server --hf-repo {new_repo_id} --hf-file {quantized_gguf_name} -c 2048
-                ```
                 """
             )
             readme_path = Path(outdir)/"README.md"
             card.save(readme_path)
+            
+
+            # Quant listesi oluşturma
+            quant_list = f"""
+## ✅ Quantized Models Download List 
+**✨ Recommended for CPU:** `Q4_K_M` | **⚡ Recommended for ARM CPU:** `Q4_0` | **🏆 Best Quality:** `Q8_0`  
+
+| 🚀 Download | 🔢 Type | 📝 Notes |
+|:---------|:-----|:------|
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q2_k.gguf) | ![Q2_K](https://img.shields.io/badge/Q2_K-1A73E8) | Basic quantization |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q3_k_s.gguf) | ![Q3_K_S](https://img.shields.io/badge/Q3_K_S-34A853) | Small size |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q3_k_m.gguf) | ![Q3_K_M](https://img.shields.io/badge/Q3_K_M-FBBC05) | Balanced quality |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q3_k_l.gguf) | ![Q3_K_L](https://img.shields.io/badge/Q3_K_L-4285F4) | Better quality |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q4_0.gguf) | ![Q4_0](https://img.shields.io/badge/Q4_0-EA4335) | Fast on ARM |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q4_k_s.gguf) | ![Q4_K_S](https://img.shields.io/badge/Q4_K_S-673AB7) | Fast, recommended |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q4_k_m.gguf) | ![Q4_K_M](https://img.shields.io/badge/Q4_K_M-673AB7) ⭐ | Best balance |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q5_0.gguf) | ![Q5_0](https://img.shields.io/badge/Q5_0-FF6D01) | Good quality |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q5_k_s.gguf) | ![Q5_K_S](https://img.shields.io/badge/Q5_K_S-0F9D58) | Balanced |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q5_k_m.gguf) | ![Q5_K_M](https://img.shields.io/badge/Q5_K_M-0F9D58) | High quality |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q6_k.gguf) | ![Q6_K](https://img.shields.io/badge/Q6_K-4285F4) 🏆 | Very good quality |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-q8_0.gguf) | ![Q8_0](https://img.shields.io/badge/Q8_0-EA4335) ⚡ | Fast, best quality |
+| [Download](https://huggingface.co/{new_repo_id}/resolve/main/{model_name.lower()}-f16.gguf) | ![F16](https://img.shields.io/badge/F16-000000) | Maximum accuracy |
+
+💡 **Tip:** Use `F16` for maximum precision when quality is critical
+"""
 
+            # README'yi güncelle (ModelCard kullanarak)
+            card.text += quant_list
+            readme_path = Path(outdir)/"README.md"
+            card.save(readme_path)
+            
             if split_model:
                 split_upload_model(str(quantized_gguf_path), outdir, new_repo_id, oauth_token, split_max_tensors, split_max_size)
             else:
@@ -424,7 +414,7 @@ with gr.Blocks(css=css) as demo:
     )
 
 def restart_space():
-    HfApi().restart_space(repo_id="ggml-org/gguf-my-repo", token=HF_TOKEN, factory_reboot=True)
+    HfApi().restart_space(repo_id="matrixportal/all-gguf-same-where", token=HF_TOKEN, factory_reboot=True)
 
 scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=21600)