Triangle104 commited on
Commit
c5c8880
1 Parent(s): 6dbcae9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -22,6 +22,27 @@ tags:
22
  This model was converted to GGUF format from [`Orion-zhen/Meissa-Qwen2.5-7B-Instruct`](https://huggingface.co/Orion-zhen/Meissa-Qwen2.5-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
23
  Refer to the [original model card](https://huggingface.co/Orion-zhen/Meissa-Qwen2.5-7B-Instruct) for more details on the model.
24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  ## Use with llama.cpp
26
  Install llama.cpp through brew (works on Mac and Linux)
27
 
 
22
  This model was converted to GGUF format from [`Orion-zhen/Meissa-Qwen2.5-7B-Instruct`](https://huggingface.co/Orion-zhen/Meissa-Qwen2.5-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
23
  Refer to the [original model card](https://huggingface.co/Orion-zhen/Meissa-Qwen2.5-7B-Instruct) for more details on the model.
24
 
25
+ ---
26
+ Model details:
27
+ -
28
+ 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".
29
+
30
+ 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.
31
+
32
+ The model is fine-tuned over Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
33
+ Training details
34
+
35
+ I used SFT method. Datasets used are listed below:
36
+
37
+ anthracite-org/stheno-filtered-v1.1
38
+ MinervaAI/Aesir-Preview
39
+ Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
40
+ anthracite-org/nopm_claude_writing_fixed
41
+ Gryphe/Sonnet3.5-Charcard-Roleplay
42
+ nothingiisreal/DirtyWritingPrompts
43
+ Orion-zhen/tagged-pixiv-novel
44
+
45
+ ---
46
  ## Use with llama.cpp
47
  Install llama.cpp through brew (works on Mac and Linux)
48