Update README.md
Browse files
README.md
CHANGED
|
@@ -37,6 +37,8 @@ Original model README [here](https://huggingface.co/Quant-Cartel/SorcererLM-8x22
|
|
| 37 |
|
| 38 |
# SorcererLM-8x22b-bf16
|
| 39 |
|
|
|
|
|
|
|
| 40 |
Oh boy, here we go. Low-rank (`r=16, alpha=32`) 16bit-LoRA on top of [WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B), trained on 2 epochs of (cleaned & deduped) c2-logs. As far as I can tell, this is an upgrade from `WizardLM-2-8x22B` for RP purposes.
|
| 41 |
|
| 42 |
Alongside this ready-to-use release I'm also releasing the LoRA itself as well as the earlier `epoch1`-checkpoint of the LoRA.
|
|
|
|
| 37 |
|
| 38 |
# SorcererLM-8x22b-bf16
|
| 39 |
|
| 40 |
+
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/6569a4ed2419be6072890cf8/L_uGojVkNUsK6QHvWgs9o.mpga"></audio>
|
| 41 |
+
|
| 42 |
Oh boy, here we go. Low-rank (`r=16, alpha=32`) 16bit-LoRA on top of [WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B), trained on 2 epochs of (cleaned & deduped) c2-logs. As far as I can tell, this is an upgrade from `WizardLM-2-8x22B` for RP purposes.
|
| 43 |
|
| 44 |
Alongside this ready-to-use release I'm also releasing the LoRA itself as well as the earlier `epoch1`-checkpoint of the LoRA.
|