Hugging Face's logo

QMB15
/
Stheno-L2-13B-8bit-exl2

Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
Inference Endpoints
Model card Files Community
QMB15 commited on
Commit
c6f2e51
•
1 Parent(s): 4b9924d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -1,3 +1,9 @@
 
 
 
 
 
 
1
  This is a exllama V2 quantization of https://huggingface.co/TheBloke/Stheno-L2-13B-GPTQ
2
  Uses a target bpw of 8, intended for best quality on cards like a 3090 or similar.
3
  Includes measurement.json for convenience of quantizing to other sizes.
@@ -5,12 +11,6 @@ Calibration data: https://huggingface.co/datasets/wikitext/resolve/refs%2Fconver
5
 
6
 
7
 
8
- ---
9
- license: llama2
10
- language:
11
- - en
12
- ---
13
-
14
  <img src="https://w.forfun.com/fetch/cb/cba2205390e517bea1ea60ca0b491af4.jpeg" style="width: 70%; min-width: 300px; display: block; margin: auto;">
15
 
16
  An experimental merging of Several Models using two various methods, [Ties-Merge](https://github.com/cg123/ties-merge) and [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient)
 
1
+ ---
2
+ license: llama2
3
+ language:
4
+ - en
5
+ ---
6
+
7
  This is a exllama V2 quantization of https://huggingface.co/TheBloke/Stheno-L2-13B-GPTQ
8
  Uses a target bpw of 8, intended for best quality on cards like a 3090 or similar.
9
  Includes measurement.json for convenience of quantizing to other sizes.
 
11
 
12
 
13
 
 
 
 
 
 
 
14
  <img src="https://w.forfun.com/fetch/cb/cba2205390e517bea1ea60ca0b491af4.jpeg" style="width: 70%; min-width: 300px; display: block; margin: auto;">
15
 
16
  An experimental merging of Several Models using two various methods, [Ties-Merge](https://github.com/cg123/ties-merge) and [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient)