Update README.md
Browse files
README.md
CHANGED
|
@@ -1,32 +1,58 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
- Epiculous/
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
tags:
|
| 7 |
-
- mergekit
|
| 8 |
- merge
|
| 9 |
-
|
| 10 |
---
|
| 11 |
-
# Violet_Twilight-v0.2
|
| 12 |
|
| 13 |
-
|
| 14 |
|
| 15 |
-
|
| 16 |
-
### Merge Method
|
| 17 |
|
| 18 |
-
|
|
|
|
| 19 |
|
| 20 |
-
|
|
|
|
| 21 |
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
-
###
|
|
|
|
| 27 |
|
| 28 |
-
|
|
|
|
|
|
|
| 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 |
+

|
| 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 |
+
```
|