Hugging Face's logo

rubra-ai
/
Phi-3-mini-128k-instruct

Text Generation
Transformers
TensorBoard
Safetensors
English
phi3
function-calling
tool-calling
agentic
rubra
conversational
custom_code
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
sanjay920 commited on
Commit
00117a9
•
1 Parent(s): 522b416

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -7
README.md CHANGED
@@ -65,13 +65,12 @@ language:
65
  ## Model description
66
  The model is the result of further post-training [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct). This model is designed for high performance in various instruction-following tasks and complex interactions, including multi-turn function calling and detailed conversations.
67
 
68
- | Model | Function Calling | MMLU | GPQA | GSM-8K | MATH | MT-bench | Win | Loss | Tie | Win Rate | Loss Rate | Adjusted Win Rate |
69
- |------------------------------------|------------------|-------|-------|--------|-------|----------|-----|------|-----|----------|-----------|-------------------|
70
- | Phi-3 Mini 128k Instruct (June) | - | - | 27.01 | - | 32.92 | - | - | - | - | - | - | - |
71
- | Rubra Enhanced Phi-3 Mini 128k Instruct (June) | - | 67.87 | 29.69 | 79.45 | 30.80 | - | - | - | - | - | - | - |
72
- | Phi-3 Mini 128k Instruct (April) | - | 68.17 | 25.90 | 80.44 | 28.12 | 7.92 | 51 | 45 | 64 | 0.31875 | 0.28125 | **0.51875** |
73
- | Rubra Enhanced Phi-3 Mini 128k Instruct (April) | 65.71% | 66.66 | 29.24 | 74.09 | 26.84 | 7.45 | 45 | 51 | 64 | 0.28125 | 0.31875 | 0.48125 |
74
-
75
  * Commit `e2ecb24bd9dae689bb30dafcf13cbbc9dbddead5` is the last commit to have the April-based Phi-3 model. The latest in main is built off the June model
76
 
77
  ## Training Data
 
65
  ## Model description
66
  The model is the result of further post-training [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct). This model is designed for high performance in various instruction-following tasks and complex interactions, including multi-turn function calling and detailed conversations.
67
 
68
+ | Model | Function Calling | MMLU | GPQA | GSM-8K | MATH | MT-bench | Win | Loss | Tie | Win Rate | Loss Rate | Adjusted Win Rate |
69
+ |----------------------------------------------|------------------|-------|-------|--------|-------|----------|-----|------|-----|----------|-----------|-------------------|
70
+ | Phi-3 Mini 128k Instruct (June) | - | 69.36 | 27.01 | 83.7 | 32.92 | - | - | - | - | - | - | - |
71
+ | Rubra Enhanced Phi-3 Mini 128k Instruct (June)| - | 67.87 | 29.69 | 79.45 | 30.80 | - | - | - | - | - | - | - |
72
+ | Phi-3 Mini 128k Instruct (April) | - | 68.17 | 25.90 | 80.44 | 28.12 | 7.92 | 51 | 45 | 64 | 0.31875 | 0.28125 | **0.51875** |
73
+ | Rubra Enhanced Phi-3 Mini 128k Instruct (April)| 65.71% | 66.66 | 29.24 | 74.09 | 26.84 | 7.45 | 45 | 51 | 64 | 0.28125 | 0.31875 | 0.48125 |
 
74
  * Commit `e2ecb24bd9dae689bb30dafcf13cbbc9dbddead5` is the last commit to have the April-based Phi-3 model. The latest in main is built off the June model
75
 
76
  ## Training Data