Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: gemma
 datasets:
 - FreedomIntelligence/ApolloMoEDataset
 language:
@@ -50,12 +50,28 @@ language:
 metrics:
 - accuracy
 base_model:
-- google/gemma-2-9b
+- FreedomIntelligence/Apollo2-9B
 pipeline_tag: question-answering
 tags:
 - biology
 - medical
 ---
+# Apollo2-9B-exl2
+Original model: [Apollo2-9B](https://huggingface.co/FreedomIntelligence/Apollo2-9B)  
+Made by: [FreedomIntelligence](https://huggingface.co/FreedomIntelligence)
+## Quants
+[4bpw h6 (main)](https://huggingface.co/cgus/Apollo2-9B-exl2/tree/main)  
+[4.5bpw h6](https://huggingface.co/cgus/Apollo2-9B-exl2/tree/4.5bpw-h6)  
+[5bpw h6](https://huggingface.co/cgus/Apollo2-9B-exl2/tree/5bpw-h6)  
+[6bpw h6](https://huggingface.co/cgus/Apollo2-9B-exl2/tree/6bpw-h6)  
+[8bpw h8](https://huggingface.co/cgus/Apollo2-9B-exl2/tree/8bpw-h8)  
+
+## Quantization notes
+Made with Exllamav2 0.2.3 with the default dataset. This model needs software with Exllamav2 library such as Text-Generation-WebUI, TabbyAPI, etc.  
+This model has to fit your GPU to be usable and it's mainly meant for RTX cards on Windows/Linux or AMD on Linux.  
+For computers with incompatible hardware it's better to use GGUF versions of the model, you can find them [here](https://huggingface.co/models?other=base_model:quantized:FreedomIntelligence/Apollo2-9B).
+
+# Original model card
 # Democratizing Medical LLMs For Much More Languages
 
 Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish, Arabic, Russian, Japanese, Korean, German, Italian, Portuguese and 38 Minor Languages So far.
@@ -68,7 +84,7 @@ Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish,
 
 
 
-![Apollo](assets/apollo_medium_final.png)
+![Apollo](https://huggingface.co/FreedomIntelligence/Apollo2-9B/blob/main/assets/apollo_medium_final.png)
 
 
 ## 🌈 Update
@@ -82,7 +98,7 @@ Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish,
 <details>
   <summary>Click to view the Languages Coverage</summary>
    
-   ![ApolloMoE](assets/languages.png)
+   ![ApolloMoE](https://huggingface.co/FreedomIntelligence/Apollo2-9B/blob/main/assets/languages.png)
 
 </details>
 
@@ -92,7 +108,7 @@ Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish,
 <details>
   <summary>Click to view the MoE routing image</summary>
 
-  ![ApolloMoE](assets/hybrid_routing.png)
+  ![ApolloMoE](https://huggingface.co/FreedomIntelligence/Apollo2-9B/blob/main/assets/hybrid_routing.png)
 
 </details>
 
@@ -106,7 +122,7 @@ Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish,
 <details>
   <summary>Click to view the Dense Models Results</summary>
 
-   ![ApolloMoE](assets/dense_results.png)
+   ![ApolloMoE](https://huggingface.co/FreedomIntelligence/Apollo2-9B/blob/main/assets/dense_results.png)
 
 </details>
 
@@ -117,7 +133,7 @@ Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish,
 <details>
   <summary>Click to view the Post-MoE Models Results</summary>
 
-   ![ApolloMoE](assets/post_moe_results.png)
+   ![ApolloMoE](https://huggingface.co/FreedomIntelligence/Apollo2-9B/blob/main/assets/post_moe_results.png)
 
 </details>
 
@@ -140,7 +156,7 @@ Covering 12 Major Languages including English, Chinese, French, Hindi, Spanish,
 
    <details><summary>Click to expand</summary>
 
-    ![ApolloMoE](assets/Dataset.png)
+    ![ApolloMoE](https://huggingface.co/FreedomIntelligence/Apollo2-9B/blob/main/assets/Dataset.png)
 
     - [Data category](https://huggingface.co/datasets/FreedomIntelligence/ApolloCorpus/tree/main/train)