Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +39 -0
- meissa-qwen2.5-7b-instruct.Q4_0.gguf +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
meissa-qwen2.5-7b-instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: gpl-3.0
|
3 |
+
base_model:
|
4 |
+
- Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
|
5 |
+
datasets:
|
6 |
+
- anthracite-org/stheno-filtered-v1.1
|
7 |
+
- MinervaAI/Aesir-Preview
|
8 |
+
- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
|
9 |
+
- anthracite-org/nopm_claude_writing_fixed
|
10 |
+
- Gryphe/Sonnet3.5-Charcard-Roleplay
|
11 |
+
- nothingiisreal/DirtyWritingPrompts
|
12 |
+
- Orion-zhen/tagged-pixiv-novel
|
13 |
+
language:
|
14 |
+
- zh
|
15 |
+
- en
|
16 |
+
pipeline_tag: text-generation
|
17 |
+
---
|
18 |
+
|
19 |
+
# Meissa-Qwen2.5-7B-Instruct
|
20 |
+
|
21 |
+
<img src="./meissa.jpg" style="align: center">
|
22 |
+
|
23 |
+
> Meissa is designated Lambda Orionis, forms Orion's head, and is a multiple star with a combined apparent magnitude of 3.33. Its name means the "shining one".
|
24 |
+
|
25 |
+
This model is fine tuned over writing and role playing datasets (maybe the first on qwen2.5-7b), aiming to enhance model's performance in novel writing and roleplaying.
|
26 |
+
|
27 |
+
The model is fine-tuned over [Orion-zhen/Qwen2.5-7B-Instruct-Uncensored](https://huggingface.co/Orion-zhen/Qwen2.5-7B-Instruct-Uncensored)
|
28 |
+
|
29 |
+
## Training details
|
30 |
+
|
31 |
+
I used SFT method. Datasets used are listed below:
|
32 |
+
|
33 |
+
- anthracite-org/stheno-filtered-v1.1
|
34 |
+
- MinervaAI/Aesir-Preview
|
35 |
+
- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
|
36 |
+
- anthracite-org/nopm_claude_writing_fixed
|
37 |
+
- Gryphe/Sonnet3.5-Charcard-Roleplay
|
38 |
+
- nothingiisreal/DirtyWritingPrompts
|
39 |
+
- Orion-zhen/tagged-pixiv-novel
|
meissa-qwen2.5-7b-instruct.Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:643fe3192af2a043041dd027fcafc97cac3317f959924e50f43040fd1aac82e5
|
3 |
+
size 4431389536
|