moelanoby commited on
Commit
e712113
·
verified ·
1 Parent(s): fa1f6ec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -34,7 +34,7 @@ The benchmark results demonstrate a level of performance that significantly surp
34
 
35
  | Model | HumanEval Pass@1 Score | Note |
36
  | :---------------------------------- | :--------------------: | :--------------------- |
37
- | **moelanoby/phi3-M3-V2 (This Model)** | **98.17%** | **Commercial License** |
38
  | GPT-4.5 / "Orion" | `~96.00%` | Projected (Late 2025) |
39
  | Gemini 2.5 Pro | `~95.00%` | Projected (Late 2025) |
40
  | Claude 4 | `~94.00%` | Projected (Late 2025) |
@@ -121,7 +121,9 @@ except AttributeError:
121
 
122
  # (Example generation code would follow here)
123
  ```
124
-
 
 
125
  ## Acknowledgements
126
 
127
  - The base of this model utilizes the **Phi-3** architecture developed by Microsoft.
 
34
 
35
  | Model | HumanEval Pass@1 Score | Note |
36
  | :---------------------------------- | :--------------------: | :--------------------- |
37
+ | **moelanoby/phi3-M3-V2 (This Model)** | **95.12%/98.17%/98.56%** | **Commercial License** and they are ordered with 0,1,2 self corrections |
38
  | GPT-4.5 / "Orion" | `~96.00%` | Projected (Late 2025) |
39
  | Gemini 2.5 Pro | `~95.00%` | Projected (Late 2025) |
40
  | Claude 4 | `~94.00%` | Projected (Late 2025) |
 
121
 
122
  # (Example generation code would follow here)
123
  ```
124
+ ## HUGE NOTES
125
+ - downside: the model might grow more incoherent and less accurate as you add more self corrections
126
+ - recommendations: you could use 1,2,3 self corrections if needed and 2 self corrections is the most recommended
127
  ## Acknowledgements
128
 
129
  - The base of this model utilizes the **Phi-3** architecture developed by Microsoft.