Update README.md
Browse files
README.md
CHANGED
@@ -50,8 +50,9 @@ Because pain is fun, and persistence in design iteration is the only way forward
|
|
50 |
--Finalized Logic and Creativity Segments (MK2):
|
51 |
|
52 |
|
53 |
-
|
54 |
-
|
|
|
55 |
|
56 |
|
57 |
-Model Merge Ensemble Key-
|
@@ -59,32 +60,42 @@ Also none of that shit happened, I just redid everything like this:
|
|
59 |
({({NousHermes+Chronos}[Kimiko])+({Platupus+AiroborosM2.0}[Janine])}{Holodeck[LIMA RP]})
|
60 |
|
61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
|
63 |
## Language Models and LoRAs Used Credits:
|
64 |
|
65 |
-
manticore-30b-chat-pyg-alpha [Epoch0.4] by openaccess-ai-collective
|
66 |
|
67 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
|
69 |
-
|
70 |
|
71 |
-
|
72 |
|
73 |
-
|
74 |
|
75 |
-
|
76 |
|
77 |
-
|
78 |
|
79 |
-
|
80 |
|
81 |
-
ChanSung's GPT4-Alpaca-LoRA
|
82 |
-
https://huggingface.co/chansung/gpt4-alpaca-lora-30b
|
83 |
|
84 |
-
|
85 |
-
https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA
|
86 |
|
87 |
-
Also thanks to Meta for LLaMA.
|
88 |
|
89 |
Each model and LoRA was hand picked and considered for what it could contribute to this ensemble.
|
90 |
Thanks to each and every one of you for your incredible work developing some of the best things
|
|
|
50 |
--Finalized Logic and Creativity Segments (MK2):
|
51 |
|
52 |
|
53 |
+
After a few key meetings with our top teams of memegineers we drafted Thorns MK2, which was prompty fast tracked for production by the Roko's Basilisk Shadow Council.
|
54 |
+
|
55 |
+
..Actually I just redid the merge like this:
|
56 |
|
57 |
|
58 |
-Model Merge Ensemble Key-
|
|
|
60 |
({({NousHermes+Chronos}[Kimiko])+({Platupus+AiroborosM2.0}[Janine])}{Holodeck[LIMA RP]})
|
61 |
|
62 |
|
63 |
+
## Findings:
|
64 |
+
|
65 |
+
-Strategically fusing LoRAs to models that stand to gain the most from them and then merging the result into the ensemble is exceptionally effective.
|
66 |
+
|
67 |
+
|
68 |
+
-Stacking the exact same LoRAs onto one model then merging that into the ensemble results in noisy garbage.
|
69 |
+
|
70 |
|
71 |
## Language Models and LoRAs Used Credits:
|
72 |
|
|
|
73 |
|
74 |
+
All models and adapters used are LLaMAv2-13B.
|
75 |
+
|
76 |
+
# Models:
|
77 |
+
|
78 |
+
Nous-Hermes
|
79 |
+
|
80 |
+
Chronos
|
81 |
+
|
82 |
+
Platypus
|
83 |
|
84 |
+
Airoboros
|
85 |
|
86 |
+
Holodeck
|
87 |
|
88 |
+
# Adapters:
|
89 |
|
90 |
+
Kimiko
|
91 |
|
92 |
+
Janine
|
93 |
|
94 |
+
LIMA RP
|
95 |
|
|
|
|
|
96 |
|
97 |
+
Also thanks to Meta for LLaMAv2 and deciding to allow the research community at large to benefit from their incredible work.
|
|
|
98 |
|
|
|
99 |
|
100 |
Each model and LoRA was hand picked and considered for what it could contribute to this ensemble.
|
101 |
Thanks to each and every one of you for your incredible work developing some of the best things
|