create readme.md
Browse files
README.md
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
datasets:
|
4 |
+
- dcbv/charluv-dataset
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
- fr
|
8 |
+
- de
|
9 |
+
library_name: transformers
|
10 |
+
pipeline_tag: text-generation
|
11 |
+
---
|
12 |
+
## Charluv-13B-Tiefighter
|
13 |
+
Tiefighter is a merged model achieved trough merging two different lora's on top of a well established existing merge.
|
14 |
+
To achieve this the following recipe was used:
|
15 |
+
|
16 |
+
We begin with the base model Undi95/Xwin-MLewd-13B-V0.2 which is a well established merged, contrary to the name this model does not have a strong NSFW bias.
|
17 |
+
Then we applied the PocketDoc/Dans-RetroRodeo-13b lora which is a finetune on the Choose your own Adventure datasets from our Skein model.
|
18 |
+
After applying this lora we merged the new model with PocketDoc/Dans-RetroRodeo-13b at 5% to weaken the newly introduced adventure bias.
|
19 |
+
The resulting merge was used as a new basemodel to which we applied Blackroot/Llama-2-13B-Storywriter-LORA and repeated the same trick, this time at 10%.
|
20 |
+
### Finally we merged the Charluv dataset and created a new basemodel out of the endresult.
|
21 |
+
### All credits for the original model goes to Henkie and the models below
|
22 |
+
|
23 |
+
This means this model contains the following ingredients from their upstream models for as far as we can track them:
|
24 |
+
|
25 |
+
Undi95/Xwin-MLewd-13B-V0.2
|
26 |
+
Undi95/ReMM-S-Light
|
27 |
+
Undi95/CreativeEngine
|
28 |
+
Brouz/Slerpeno
|
29 |
+
elinas/chronos-13b-v2
|
30 |
+
jondurbin/airoboros-l2-13b-2.1
|
31 |
+
NousResearch/Nous-Hermes-Llama2-13b+nRuaif/Kimiko-v2
|
32 |
+
CalderaAI/13B-Legerdemain-L2+lemonilia/limarp-llama2-v2
|
33 |
+
KoboldAI/LLAMA2-13B-Holodeck-1
|
34 |
+
NousResearch/Nous-Hermes-13b
|
35 |
+
OpenAssistant/llama2-13b-orca-8k-3319
|
36 |
+
ehartford/WizardLM-1.0-Uncensored-Llama2-13b
|
37 |
+
Henk717/spring-dragon
|
38 |
+
The-Face-Of-Goonery/Huginn-v3-13b (Contains undisclosed model versions, those we assumed where possible)
|
39 |
+
SuperCOT (Undisclosed version)
|
40 |
+
elinas/chronos-13b-v2 (Version assumed)
|
41 |
+
NousResearch/Nous-Hermes-Llama2-13b
|
42 |
+
stabilityai/StableBeluga-13B (Version assumed)
|
43 |
+
zattio770/120-Days-of-LORA-v2-13B
|
44 |
+
PygmalionAI/pygmalion-2-13b
|
45 |
+
Undi95/Storytelling-v1-13B-lora
|
46 |
+
TokenBender/sakhi_13B_roleplayer_NSFW_chat_adapter
|
47 |
+
nRuaif/Kimiko-v2-13B
|
48 |
+
The-Face-Of-Goonery/Huginn-13b-FP16
|
49 |
+
"a lot of different models, like hermes, beluga, airoboros, chronos.. limarp"
|
50 |
+
lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
|
51 |
+
Xwin-LM/Xwin-LM-13B-V0.2
|
52 |
+
PocketDoc/Dans-RetroRodeo-13b
|
53 |
+
Blackroot/Llama-2-13B-Storywriter-LORA
|