Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
|
4 |
+
license: gpl-3.0
|
5 |
+
base_model:
|
6 |
+
- Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
|
7 |
+
datasets:
|
8 |
+
- anthracite-org/stheno-filtered-v1.1
|
9 |
+
- MinervaAI/Aesir-Preview
|
10 |
+
- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
|
11 |
+
- anthracite-org/nopm_claude_writing_fixed
|
12 |
+
- Gryphe/Sonnet3.5-Charcard-Roleplay
|
13 |
+
- nothingiisreal/DirtyWritingPrompts
|
14 |
+
- Orion-zhen/tagged-pixiv-novel
|
15 |
+
language:
|
16 |
+
- zh
|
17 |
+
- en
|
18 |
+
pipeline_tag: text-generation
|
19 |
+
|
20 |
+
---
|
21 |
+
|
22 |
+
[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
|
23 |
+
|
24 |
+
|
25 |
+
# QuantFactory/Meissa-Qwen2.5-7B-Instruct-GGUF
|
26 |
+
This is quantized version of [Orion-zhen/Meissa-Qwen2.5-7B-Instruct](https://huggingface.co/Orion-zhen/Meissa-Qwen2.5-7B-Instruct) created using llama.cpp
|
27 |
+
|
28 |
+
# Original Model Card
|
29 |
+
|
30 |
+
|
31 |
+
# Meissa-Qwen2.5-7B-Instruct
|
32 |
+
|
33 |
+
<img src="./meissa.jpg" style="align: center">
|
34 |
+
|
35 |
+
> 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".
|
36 |
+
|
37 |
+
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.
|
38 |
+
|
39 |
+
The model is fine-tuned over [Orion-zhen/Qwen2.5-7B-Instruct-Uncensored](https://huggingface.co/Orion-zhen/Qwen2.5-7B-Instruct-Uncensored)
|
40 |
+
|
41 |
+
## Training details
|
42 |
+
|
43 |
+
I used SFT method. Datasets used are listed below:
|
44 |
+
|
45 |
+
- anthracite-org/stheno-filtered-v1.1
|
46 |
+
- MinervaAI/Aesir-Preview
|
47 |
+
- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
|
48 |
+
- anthracite-org/nopm_claude_writing_fixed
|
49 |
+
- Gryphe/Sonnet3.5-Charcard-Roleplay
|
50 |
+
- nothingiisreal/DirtyWritingPrompts
|
51 |
+
- Orion-zhen/tagged-pixiv-novel
|
52 |
+
|