Fischerboot commited on
Commit
b3f184c
1 Parent(s): 0b53070

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -3
README.md CHANGED
@@ -1,3 +1,42 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
4
+ license: apache-2.0
5
+ ---
6
+ ![download.png](https://raw.githubusercontent.com/Fischherboot/Aculi/main/watermark-no-bg.png)
7
+
8
+
9
+ # mistral-doryV2-12b-GGUF
10
+
11
+ # Original Modelcard:
12
+
13
+
14
+ # Dory 12b (v2)
15
+ (redone) redone instruct finetune of mistral nemo 12b's base. *not* (E)RP-focused, leave that to drummer.
16
+
17
+ ![image/gif](https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/BiBtgV_WEIha72WqETWfk.gif)
18
+
19
+ thanks to twisted again for the compute :3
20
+
21
+ ## Prompting
22
+ alpaca-like:
23
+ ```
24
+ ### System:
25
+ [Optional system prompt]
26
+
27
+ ### Instruction:
28
+ [Query]
29
+
30
+ ### Response:
31
+ [Response]</s>
32
+
33
+ ### Instruction:
34
+ [...]
35
+ ```
36
+
37
+ ## Training details
38
+ Rank 64 QDoRA, trained on the following data mix:
39
+ - All of [kalomaze/Opus_Instruct_3k](https://huggingface.co/datasets/kalomaze/Opus_Instruct_3k)
40
+ - All conversations with a reward model rating above 5 in [Magpie-Align/Magpie-Gemma2-Pro-Preview-Filtered](https://huggingface.co/datasets/Magpie-Align/Magpie-Gemma2-Pro-Preview-Filtered)
41
+ - 50k of [Gryphe/Sonnet3.5-SlimOrcaDedupCleaned](https://huggingface.co/datasets/Gryphe/Sonnet3.5-SlimOrcaDedupCleaned)
42
+ - All stories above 4.7 rating and published before 2020 in [Fizzarolli/FallingThroughTheSkies-592k-Filtered-Filtered](https://huggingface.co/datasets/Fizzarolli/FallingThroughTheSkies-592k-Filtered-Filtered)