Text Generation
GGUF
chat
Inference Endpoints
conversational
aashish1904 commited on
Commit
4c0289e
·
verified ·
1 Parent(s): ec0a45d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+
4
+ license: apache-2.0
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - chat
8
+ base_model:
9
+ - Gryphe/Pantheon-RP-1.6-12b-Nemo
10
+ - Sao10K/MN-12B-Lyra-v3
11
+ - anthracite-org/magnum-v2.5-12b-kto
12
+ - nbeerbower/mistral-nemo-bophades-12B
13
+
14
+ ---
15
+
16
+ ![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)
17
+
18
+ # QuantFactory/StarDust-12b-v1-GGUF
19
+ This is quantized version of [Luni/StarDust-12b-v1](https://huggingface.co/Luni/StarDust-12b-v1) created using llama.cpp
20
+
21
+ # Original Model Card
22
+
23
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6303fa71fc783bfc7443e7ae/qRsB-uefbKKrAqxknbWtN.png)
24
+
25
+
26
+ # StarDust-12b-v1
27
+
28
+ ## Quants
29
+
30
+ - GGUF: [mradermacher/StarDust-12b-v1-GGUF](https://huggingface.co/mradermacher/StarDust-12b-v1-GGUF)
31
+ - weighted/imatrix GGUF [mradermacher/StarDust-12b-v1-i1-GGUF](https://huggingface.co/mradermacher/StarDust-12b-v1-i1-GGUF)
32
+ - exl2: [lucyknada/Luni_StarDust-12b-v1-exl2](https://huggingface.co/lucyknada/Luni_StarDust-12b-v1-exl2)
33
+
34
+ ## Description | Usecase
35
+
36
+ The result of this merge is in my opinion a more vibrant and less generic sonnet inspired prose, it's able to be gentle and harsh where asked.
37
+ I've personally been trying to get a more spice while also compensating for the Magnum-v2.5 having the issue on my end that it simply won't stop yapping.
38
+
39
+ - This model is intended to be used as a Role-playing model.
40
+ - Its direct conversational output is... I can't even say it's luck, it's just not made for it.
41
+ - Extension to Conversational output: The Model is designed for roleplay, direct instructing or general purpose is NOT recommended.
42
+
43
+ ## Initial Feedback
44
+
45
+ Initial feedback shows that the model has a tendency to promote flirting. If this becomes too much try to steer the model with a system prompt to focus on SFW and on-flirty interactions.
46
+
47
+ ## Prompting
48
+
49
+ ### Edit: ChatML has proven to be the BEST choice.
50
+
51
+ Both Mistral and ChatML should work though I had better results with ChatML:
52
+ ChatML Example:
53
+ ```py
54
+ """<|im_start|>user
55
+ Hi there!<|im_end|>
56
+ <|im_start|>assistant
57
+ Nice to meet you!<|im_end|>
58
+ <|im_start|>user
59
+ Can I ask a question?<|im_end|>
60
+ <|im_start|>assistant
61
+ """
62
+ ```
63
+
64
+
65
+
66
+ ## Merge Details
67
+ ### Merge Method
68
+
69
+ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Sao10K/MN-12B-Lyra-v3](https://huggingface.co/Sao10K/MN-12B-Lyra-v3) as a base.
70
+
71
+ ### Models Merged
72
+
73
+ The following models were included in the merge:
74
+ * [Gryphe/Pantheon-RP-1.6-12b-Nemo](https://huggingface.co/Gryphe/Pantheon-RP-1.6-12b-Nemo)
75
+ * [anthracite-org/magnum-v2.5-12b-kto](https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto)
76
+ * [nbeerbower/mistral-nemo-bophades-12B](https://huggingface.co/nbeerbower/mistral-nemo-bophades-12B)
77
+ * [Sao10K/MN-12B-Lyra-v3](https://huggingface.co/Sao10K/MN-12B-Lyra-v3)
78
+
79
+ ### Special Thanks
80
+
81
+ Special thanks to the SillyTilly and myself for helping me find the energy to finish this.