Darkknight535 commited on
Commit
c43b849
·
verified ·
1 Parent(s): 0e9c8b2

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ moonlight-l3-15b-16k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ moonlight-l3-15b-16k.bf16.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - not-for-all-audiences
5
+ - autoquant
6
+ - gguf
7
+ ---
8
+ ### MoonLight-L3-15B
9
+ ---
10
+ ![Waifu](https://huggingface.co/Darkknight535/)
11
+ ---
12
+ - **Enhancements**:
13
+ - **Fine-tuning**: The model has undergone fine-tuning on different RP datasheets and some dark nsfw datasheets.
14
+
15
+ ---
16
+
17
+ ### Instruct Template
18
+ Default llama3 instruct and context preset, but here is the one i use.
19
+ [Instruct](https://huggingface.co/Darkknight535/OpenCrystal-12B-L3/blob/main/Llama%203%20%5BInstruct%5D.json)
20
+ [Context](https://huggingface.co/Darkknight535/OpenCrystal-12B-L3/blob/main/Llama%203%20%5BContext%5D.json)
21
+
22
+ ### Samplers
23
+
24
+
25
+ ## Creative
26
+ ```
27
+ Temp : 1.2
28
+ Min P : 0.05
29
+ Repetition Penalty : 1.05
30
+
31
+ [And everything else neutral] (DRY Sampler Breaks it)
32
+ ```
33
+
34
+ ## Normal(Precise)
35
+ ```
36
+ Temp : 0.6 - 0.8
37
+ Min P : 0.1
38
+ Repetition Penalty : 1.1
39
+
40
+ [And everything else neutral](DRY Sampler Breaks it)
41
+ ```
42
+
43
+ ### Features
44
+ - Supports 16k through rope scaling (finetuned on a 16k datasheet)
45
+ - Automatically speaks as other NPCs.
46
+ - Creative output(Like the OpenCrystal 12b but more coherent).
47
+ - Coherent responses(Accuatlly having 15B model logic).
48
+ - Output feels similar to using Character.ai
49
+ - Improved adherence to prompts.
50
+ - No hallucinations (15B).
51
+ - Capable of summarizing and generating image prompts well. (The above image's prompt was generated in a roleplay by this model; possible due to the Llama-3-instruct base.)
52
+
53
+ ### System Prompt
54
+ ```
55
+ Develop the plot slowly, always stay in character. Describe all actions in full, elaborate, explicit, graphic, and vivid detail. Mention all relevant sensory perceptions. Keep the story immersive and engaging. Speak as other person when needed and prefix with the name of person you're speaking as except {{user}}.
56
+ ```
57
+
58
+ ### FeedBack
59
+ [FeedBack here](https://huggingface.co/Darkknight535/Darkknight535/Moonlight-L3-15B-16k/discussions/1)
moonlight-l3-15b-16k.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccddb37e5cc4ab94de3e35574b595d19601fde85a02ebf814b7b9ecfc5e6cedb
3
+ size 5747111360
moonlight-l3-15b-16k.bf16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a44b6f52903636f1fa1a94b8779a0387bcfef15f785446bfeb7eae8a304a1d84
3
+ size 30028600768