Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ This model started as a block-diagonal [frankenllama merge](https://huggingface.
|
|
| 6 |
|
| 7 |
However due to some anomaly likely caused by the novel methods used by MythoMax I was unable to initiate the LoRA training needed to bring the resulting model back to order.
|
| 8 |
|
| 9 |
-
Being a [Chronorctypus-Limarobormes](https://huggingface.co/chargoddard/Chronorctypus-Limarobormes-13b) enjoyer I decided to look further into the TIES-merging that it utilizes- as cited in
|
| 10 |
)
|
| 11 |
|
| 12 |
I used [llama2-22b](https://huggingface.co/chargoddard/llama2-22b) as the base model upon which I merged the MythoMax/Enterredaas frankenmerge, [Dendrite-II](https://huggingface.co/Envoid/Dendrite-II-22B) and [Bacchus](https://huggingface.co/Envoid/Bacchus-22B)
|
|
|
|
| 6 |
|
| 7 |
However due to some anomaly likely caused by the novel methods used by MythoMax I was unable to initiate the LoRA training needed to bring the resulting model back to order.
|
| 8 |
|
| 9 |
+
Being a [Chronorctypus-Limarobormes](https://huggingface.co/chargoddard/Chronorctypus-Limarobormes-13b) enjoyer I decided to look further into the TIES-merging that it utilizes- as cited in the arXiv paper: [Resolving Interference When Merging Models](https://huggingface.co/papers/2306.01708
|
| 10 |
)
|
| 11 |
|
| 12 |
I used [llama2-22b](https://huggingface.co/chargoddard/llama2-22b) as the base model upon which I merged the MythoMax/Enterredaas frankenmerge, [Dendrite-II](https://huggingface.co/Envoid/Dendrite-II-22B) and [Bacchus](https://huggingface.co/Envoid/Bacchus-22B)
|