Update README.md
Browse files
    	
        README.md
    CHANGED
    
    | @@ -14,4 +14,77 @@ tags: | |
| 14 | 
             
            The BigWeave models aim to experimentally identify merge settings for increasing model performance. The version number merely tracks various attempts and is not a quality indicator. Only results demonstrating good performance are retained and shared.
         | 
| 15 |  | 
| 16 | 
             
            # Prompting Format
         | 
| 17 | 
            -
            Mistral, Vicuna and Alpaca.
         | 
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 14 | 
             
            The BigWeave models aim to experimentally identify merge settings for increasing model performance. The version number merely tracks various attempts and is not a quality indicator. Only results demonstrating good performance are retained and shared.
         | 
| 15 |  | 
| 16 | 
             
            # Prompting Format
         | 
| 17 | 
            +
            Mistral, Vicuna and Alpaca.
         | 
| 18 | 
            +
             | 
| 19 | 
            +
            # Merge process
         | 
| 20 | 
            +
            This is a self-merge of 152334H/miqu-1-70b-sf. By conducting exl2 measurements, we identify the most relevant layers. The layers are duplicated such that each group consists of consecutive layers with a two-layer overlap (i.e. larger groups than in v15).
         | 
| 21 | 
            +
             | 
| 22 | 
            +
            Merge configuration:
         | 
| 23 | 
            +
            ```
         | 
| 24 | 
            +
            slices:
         | 
| 25 | 
            +
              - sources:
         | 
| 26 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 27 | 
            +
                  layer_range: [0,11]
         | 
| 28 | 
            +
              - sources:
         | 
| 29 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 30 | 
            +
                  layer_range: [9,13]
         | 
| 31 | 
            +
              - sources:
         | 
| 32 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 33 | 
            +
                  layer_range: [11,15]
         | 
| 34 | 
            +
              - sources:
         | 
| 35 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 36 | 
            +
                  layer_range: [13,17]
         | 
| 37 | 
            +
              - sources:
         | 
| 38 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 39 | 
            +
                  layer_range: [15,23]
         | 
| 40 | 
            +
              - sources:
         | 
| 41 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 42 | 
            +
                  layer_range: [21,25]
         | 
| 43 | 
            +
              - sources:
         | 
| 44 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 45 | 
            +
                  layer_range: [23,49]
         | 
| 46 | 
            +
              - sources:
         | 
| 47 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 48 | 
            +
                  layer_range: [47,51]
         | 
| 49 | 
            +
              - sources:
         | 
| 50 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 51 | 
            +
                  layer_range: [49,53]
         | 
| 52 | 
            +
              - sources:
         | 
| 53 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 54 | 
            +
                  layer_range: [51,55]
         | 
| 55 | 
            +
              - sources:
         | 
| 56 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 57 | 
            +
                  layer_range: [53,57]
         | 
| 58 | 
            +
              - sources:
         | 
| 59 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 60 | 
            +
                  layer_range: [55,59]
         | 
| 61 | 
            +
              - sources:
         | 
| 62 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 63 | 
            +
                  layer_range: [57,61]
         | 
| 64 | 
            +
              - sources:
         | 
| 65 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 66 | 
            +
                  layer_range: [59,63]
         | 
| 67 | 
            +
              - sources:
         | 
| 68 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 69 | 
            +
                  layer_range: [61,65]
         | 
| 70 | 
            +
              - sources:
         | 
| 71 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 72 | 
            +
                  layer_range: [63,67]
         | 
| 73 | 
            +
              - sources:
         | 
| 74 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 75 | 
            +
                  layer_range: [65,69]
         | 
| 76 | 
            +
              - sources:
         | 
| 77 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 78 | 
            +
                  layer_range: [67,71]
         | 
| 79 | 
            +
              - sources:
         | 
| 80 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 81 | 
            +
                  layer_range: [69,73]
         | 
| 82 | 
            +
              - sources:
         | 
| 83 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 84 | 
            +
                  layer_range: [71,75]
         | 
| 85 | 
            +
              - sources:
         | 
| 86 | 
            +
                - model: 152334H/miqu-1-70b-sf
         | 
| 87 | 
            +
                  layer_range: [73,80]
         | 
| 88 | 
            +
            merge_method: passthrough
         | 
| 89 | 
            +
            dtype: float16
         | 
| 90 | 
            +
            ```
         | 
