Epiculous commited on
Commit
701432d
1 Parent(s): 1f0d55d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -19
README.md CHANGED
@@ -1,32 +1,58 @@
1
  ---
2
- base_model:
3
- - Epiculous/Azure_Dusk-v0.2
4
- - Epiculous/Crimson_Dawn-V0.2
5
- library_name: transformers
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  tags:
7
- - mergekit
8
  - merge
9
-
10
  ---
11
- # Violet_Twilight-v0.2
12
 
13
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
 
15
- ## Merge Details
16
- ### Merge Method
17
 
18
- This model was merged using the SLERP merge method.
 
19
 
20
- ### Models Merged
 
21
 
22
- The following models were included in the merge:
23
- * [Epiculous/Azure_Dusk-v0.2](https://huggingface.co/Epiculous/Azure_Dusk-v0.2)
24
- * [Epiculous/Crimson_Dawn-V0.2](https://huggingface.co/Epiculous/Crimson_Dawn-V0.2)
 
 
 
 
 
 
25
 
26
- ### Configuration
 
27
 
28
- The following YAML configuration was used to produce this model:
 
 
29
 
 
 
30
  ```yaml
31
  slices:
32
  - sources:
@@ -42,7 +68,7 @@ parameters:
42
  value: [0, 0.5, 0.3, 0.7, 1]
43
  - filter: mlp
44
  value: [1, 0.5, 0.7, 0.3, 0]
45
- - value: 0.5
46
  dtype: bfloat16
47
 
48
- ```
 
1
  ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
5
+ - anthracite-org/stheno-filtered-v1.1
6
+ - PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
7
+ - Gryphe/Sonnet3.5-Charcard-Roleplay
8
+ - Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
9
+ - anthracite-org/kalo-opus-instruct-22k-no-refusal
10
+ - anthracite-org/nopm_claude_writing_fixed
11
+ - anthracite-org/kalo_opus_misc_240827
12
+ language:
13
+ - en
14
+ - fr
15
+ - de
16
+ - es
17
+ - it
18
+ - pt
19
+ - ru
20
+ - zh
21
+ - ja
22
+ pipeline_tag: text-generation
23
  tags:
 
24
  - merge
 
25
  ---
 
26
 
27
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64adfd277b5ff762771e4571/P962FQhRG4I8nbU_DJolY.png)
28
 
29
+ Now for something a bit different, Violet_Twilight-v0.2! This model is a SLERP merge of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2!
 
30
 
31
+ # Quants!
32
+ <strong>full</strong> / [exl2]() / [gguf]()
33
 
34
+ ## Prompting
35
+ The v0.2 models are trained on ChatML, the prompting structure goes a little something like this:
36
 
37
+ ```
38
+ <|im_start|>user
39
+ Hi there!<|im_end|>
40
+ <|im_start|>assistant
41
+ Nice to meet you!<|im_end|>
42
+ <|im_start|>user
43
+ Can I ask a question?<|im_end|>
44
+ <|im_start|>assistant
45
+ ```
46
 
47
+ ### Context and Instruct
48
+ The v0.2 models are trained on ChatML, please use that Context and Instruct template.
49
 
50
+ ### Current Top Sampler Settings
51
+ [Spicy_Temp](https://files.catbox.moe/9npj0z.json) <br/>
52
+ [Violet_Twilight-Nitral-Special](https://files.catbox.moe/ot54u3.json) <br/>
53
 
54
+ ## Merging
55
+ The following config was used to merge Azure Dusk and Crimson Dawn
56
  ```yaml
57
  slices:
58
  - sources:
 
68
  value: [0, 0.5, 0.3, 0.7, 1]
69
  - filter: mlp
70
  value: [1, 0.5, 0.7, 0.3, 0]
71
+ - value: 0.5 # fallback for rest of tensors
72
  dtype: bfloat16
73
 
74
+ ```