InferenceIllusionist commited on
Commit
d6feede
1 Parent(s): de82d77

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -3
README.md CHANGED
@@ -1,3 +1,37 @@
1
- ---
2
- license: cc-by-nc-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model_relation: quantized
4
+ quantized_by: Quant-Cartel
5
+ base_model: Envoid/Mistral-Small-NovusKyver
6
+ pipeline_tag: text-generation
7
+ tags:
8
+ - not-for-all-audiences
9
+ - iMat
10
+ - GGUF
11
+ ---
12
+ ```
13
+ e88 88e d8
14
+ d888 888b 8888 8888 ,"Y88b 888 8e d88
15
+ C8888 8888D 8888 8888 "8" 888 888 88b d88888
16
+ Y888 888P Y888 888P ,ee 888 888 888 888
17
+ "88 88" "88 88" "88 888 888 888 888
18
+ b
19
+ 8b,
20
+
21
+ e88'Y88 d8 888
22
+ d888 'Y ,"Y88b 888,8, d88 ,e e, 888
23
+ C8888 "8" 888 888 " d88888 d88 88b 888
24
+ Y888 ,d ,ee 888 888 888 888 , 888
25
+ "88,d88 "88 888 888 888 "YeeP" 888
26
+
27
+ PROUDLY PRESENTS
28
+ ```
29
+ # Mistral-Small-NovusKyver-iMat-GGUF
30
+ Quantized with love from fp32.
31
+
32
+ Original model author: [envoid](https://huggingface.co/Envoid/)
33
+
34
+ * Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) in 105 chunks, n_ctx=512, and fp32 precision weights
35
+
36
+ Original model README [here](https://huggingface.co/Envoid/Mistral-Small-NovusKyver/) and below:
37
+