File size: 563 Bytes
dea7828 17c2b36 c5f32ce |
1 2 3 4 5 6 7 8 9 |
---
license: bigscience-openrail-m
---
- A distilled version of a merge of starchat_beta (60%), starcoderplus(20%) and starcoder(20%), using layer removal and merging.
- The layers are merged or removed as follows. the index numbers are the layer from the original model. two or more indexes means these layers are averaged.:
[[0], [1], [2], [3], [4], [5], [6], [7], [8, 9], [10], [11], [13], [14], [15, 16], [17], [18], [19, 20], [21], [22], [23], [24], [27], [28], [29], [30], [31, 32], [33], [34], [36], [37], [39]]
- TODO: finetuning still required
|