Update README.md

README.md

@@ -1,8 +1,6 @@
 ---
 base_model:
 - Undi95/Llama-3-Unholy-8B
-- Locutusque/llama-3-neural-chat-v1-8b
-- ruslanmv/Medical-Llama3-8B-16bit
 library_name: transformers
 tags:
 - mergekit
@@ -18,7 +16,7 @@ datasets:
 - MaziyarPanahi/WizardLM_evol_instruct_V2_196k
 - ruslanmv/ai-medical-chatbot
 model-index:
-- name: Medichat-Llama3-8B
+- name: Ryeta-0
   results:
   - task:
       type: text-generation
@@ -34,10 +32,7 @@ model-index:
     - type: acc_norm
       value: 59.13
       name: normalized accuracy
-    source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
-      name: Open LLM Leaderboard
+    
   - task:
       type: text-generation
       name: Text Generation
@@ -51,10 +46,7 @@ model-index:
     - type: acc_norm
       value: 82.9
       name: normalized accuracy
-    source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
-      name: Open LLM Leaderboard
+   
   - task:
       type: text-generation
       name: Text Generation
@@ -69,10 +61,7 @@ model-index:
     - type: acc
       value: 60.35
       name: accuracy
-    source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
-      name: Open LLM Leaderboard
+    
   - task:
       type: text-generation
       name: Text Generation
@@ -86,10 +75,7 @@ model-index:
     metrics:
     - type: mc2
       value: 49.65
-    source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
-      name: Open LLM Leaderboard
+  
   - task:
       type: text-generation
       name: Text Generation
@@ -104,10 +90,7 @@ model-index:
     - type: acc
       value: 78.93
       name: accuracy
-    source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
-      name: Open LLM Leaderboard
+    
   - task:
       type: text-generation
       name: Text Generation
@@ -122,64 +105,36 @@ model-index:
     - type: acc
       value: 60.35
       name: accuracy
-    source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
-      name: Open LLM Leaderboard
+    
 language:
 - en
 ---
 
-### Medichat-Llama3-8B
+### Ryeta-0
 
 Built upon the powerful LLaMa-3 architecture and fine-tuned on an extensive dataset of health information, this model leverages its vast medical knowledge to offer clear, comprehensive answers.
 
 This model is generally better for accurate and informative responses, particularly for users seeking in-depth medical advice.
 
 
-The following YAML configuration was used to produce this model:
-
-```yaml
-
-models:
-  - model: Undi95/Llama-3-Unholy-8B
-    parameters:
-      weight: [0.25, 0.35, 0.45, 0.35, 0.25]
-      density: [0.1, 0.25, 0.5, 0.25, 0.1]
-  - model: Locutusque/llama-3-neural-chat-v1-8b
-  - model: ruslanmv/Medical-Llama3-8B-16bit
-    parameters:
-      weight: [0.55, 0.45, 0.35, 0.45, 0.55]
-      density: [0.1, 0.25, 0.5, 0.25, 0.1]
-merge_method: dare_ties
-base_model: Locutusque/llama-3-neural-chat-v1-8b
-parameters:
-  int8_mask: true
-dtype: bfloat16
-
-```
-
-# Comparision Against Dr.Samantha 7B
-
-| Subject                 | Medichat-Llama3-8B Accuracy (%) | Dr. Samantha Accuracy (%) |
-|-------------------------|---------------------------------|---------------------------|
-| Clinical Knowledge      | 71.70                           | 52.83                     |
-| Medical Genetics        | 78.00                           | 49.00                     |
-| Human Aging             | 70.40                           | 58.29                     |
-| Human Sexuality         | 73.28                           | 55.73                     |
-| College Medicine        | 62.43                           | 38.73                     |
-| Anatomy                 | 64.44                           | 41.48                     |
-| College Biology         | 72.22                           | 52.08                     |
-| High School Biology     | 77.10                           | 53.23                     |
-| Professional Medicine   | 63.97                           | 38.73                     |
-| Nutrition               | 73.86                           | 50.33                     |
-| Professional Psychology | 68.95                           | 46.57                     |
-| Virology                | 54.22                           | 41.57                     |
-| High School Psychology  | 83.67                           | 66.60                     |
-| **Average**             | **70.33**                       | **48.85**                 |
-
-
-The current model demonstrates a substantial improvement over the previous [Dr. Samantha](sethuiyer/Dr_Samantha-7b) model in terms of subject-specific knowledge and accuracy.
+# Benchmarks
+
+| Subject                 | Medichat-Llama3-8B Accuracy (%) | |
+|-------------------------|---------------------------------|
+| Clinical Knowledge      | 71.70                           |
+| Medical Genetics        | 78.00                           |
+| Human Aging             | 70.40                           |
+| Human Sexuality         | 73.28                           |
+| College Medicine        | 62.43                           | 
+| Anatomy                 | 64.44                           | 
+| College Biology         | 72.22                           | 
+| High School Biology     | 77.10                           |
+| Professional Medicine   | 63.97                           |
+| Nutrition               | 73.86                           |
+| Professional Psychology | 68.95                           |
+| Virology                | 54.22                           |
+  | High School Psychology  | 83.67                         |
+| **Average**             | **70.33**                       |
 
 ### Usage:
 ```python
@@ -187,7 +142,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 class MedicalAssistant:
-    def __init__(self, model_name="sethuiyer/Medichat-Llama3-8B", device="cuda"):
+    def __init__(self, model_name="SpectreLynx/Ryeta-0", device="cuda"):
         self.device = device
         self.tokenizer = AutoTokenizer.from_pretrained(model_name)
         self.model = AutoModelForCausalLM.from_pretrained(model_name).to(self.device)
@@ -224,12 +179,3 @@ if __name__ == "__main__":
     print(response)
 
 ```
-
-## Quants
-Thanks to [Quant Factory](https://huggingface.co/QuantFactory), the quantized version of this model is available at [QuantFactory/Medichat-Llama3-8B-GGUF](https://huggingface.co/QuantFactory/Medichat-Llama3-8B-GGUF),
-
-
-## Ollama
-This model is now also available on Ollama. You can use it by running the command ```ollama run monotykamary/medichat-llama3``` in your 
-terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on 
-a Google Colab backend.