Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
| 4 |
-
EXPERIMENTAL
|
| 5 |
-
|
| 6 |
[GPlatty-30B](https://huggingface.co/lilloukas/GPlatty-30B) merged with bhenrym14's [airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-LoRA](https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-LoRA), full model (FP16)
|
| 7 |
|
| 8 |
More info about the LoRA [Here](https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-LoRA). This is an alternative to SuperHOT 8k LoRA trained with LoRA_rank 64 and context extended to 16K, with airoboros 1.4.1 dataset.
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
|
|
|
|
|
|
| 4 |
[GPlatty-30B](https://huggingface.co/lilloukas/GPlatty-30B) merged with bhenrym14's [airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-LoRA](https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-LoRA), full model (FP16)
|
| 5 |
|
| 6 |
More info about the LoRA [Here](https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-LoRA). This is an alternative to SuperHOT 8k LoRA trained with LoRA_rank 64 and context extended to 16K, with airoboros 1.4.1 dataset.
|