README.md

metadata

base_model:
  - aihub-app/zyte-1B
  - appvoid/palmer-002-2401
  - vihangd/DopeyTinyLlama-1.1B-v1
tags:
  - mergekit
  - merge

palmer

This is a merge of pre-trained language models created using mergekit.

### Evaluation
                   ARC-C     OBQA   HellaSwag  PIQA  Winogrande Average
tinyllama        | 0.3029 | 0.3600 | 0.5935 | 0.7329 | 0.5959 | 0.5170 |
palmer-002-2402  | 0.3311 | 0.3600 | 0.5981 | 0.7416 | 0.6006 | 0.5266 |
tinyllama-chat   | 0.3285 | 0.3740 | 0.6037 | 0.7448 | 0.6022 | 0.5306 |
zyte-1b		     | 0.3353 | 0.3700 | 0.6086 | 0.7541 | 0.5998 | 0.5335 |
babbage-002      | 0.3285 | 0.3620 | 0.6380 | 0.7606 | 0.6085 | 0.5395 |
palmer-003       | 0.3370 | 0.3740 | 0.6128 | 0.7486 | 0.6535 | 0.5451 |

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• aihub-app/zyte-1B
• appvoid/palmer-002-2401
• vihangd/DopeyTinyLlama-1.1B-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: aihub-app/zyte-1B
    parameters:
      weight: 1.0
  - model: appvoid/palmer-002-2401
    parameters:
      weight: 0.75
  - model: vihangd/DopeyTinyLlama-1.1B-v1
    parameters:
      weight: 0.75
merge_method: linear
dtype: float16