Update README.md
Browse files
README.md
CHANGED
@@ -23,32 +23,6 @@ metrics:
|
|
23 |
pipeline_tag: text-generation
|
24 |
---
|
25 |
|
26 |
-
## 13B-Ouroboros
|
27 |
-
Ouroboros is an experimental model based on Meta's LLaMA [v1] 13B base model with a merging technique optimized per layer---
|
28 |
-
tags:
|
29 |
-
- llama
|
30 |
-
- alpaca
|
31 |
-
- vicuna
|
32 |
-
- uncensored
|
33 |
-
- merge
|
34 |
-
- mix
|
35 |
-
- airoboros
|
36 |
-
- openorca
|
37 |
-
- orcamini
|
38 |
-
- orca
|
39 |
-
- instruct
|
40 |
-
- mixtune
|
41 |
-
datasets:
|
42 |
-
- Open-Orca/OpenOrca
|
43 |
-
- anon8231489123/ShareGPT_Vicuna_unfiltered
|
44 |
-
- jondurbin/airoboros-uncensored
|
45 |
-
language:
|
46 |
-
- en
|
47 |
-
metrics:
|
48 |
-
- accuracy
|
49 |
-
pipeline_tag: text-generation
|
50 |
-
---
|
51 |
-
|
52 |
## 13B-Ouroboros
|
53 |
Ouroboros is an experimental model based on Meta's LLaMA [v1] 13B base model using a custom merging technique, tweaking
|
54 |
each layer's merge % based on internal tests against the PTB dataset, scoring ~26.31 according to internal evaluation
|
|
|
23 |
pipeline_tag: text-generation
|
24 |
---
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
## 13B-Ouroboros
|
27 |
Ouroboros is an experimental model based on Meta's LLaMA [v1] 13B base model using a custom merging technique, tweaking
|
28 |
each layer's merge % based on internal tests against the PTB dataset, scoring ~26.31 according to internal evaluation
|