Hugging Face's logo

ReadyArt
/
Llama_3.x_70b_Hexagon_Purple_V2_EXL2_8.0bpw_H8

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
exl2
8-bit precision
conversational
text-generation-inference
Model card Files Community
ArtusDev commited on
Commit
18bb216
·
verified ·
1 Parent(s): 87f21b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -6
README.md CHANGED
@@ -1,17 +1,18 @@
1
  ---
2
  base_model:
3
- - Steelskull/L3.3-Electra-R1-70b
4
- - Nexesenex/Llama_3.x_70b_SmarTracks_V1.01
5
- - NexesMess/Llama_3.3_70b_DoppelGanger_R1
6
- - nbeerbower/Llama3.1-Gutenberg-Doppel-70B
7
- - NexesMess/Llama_3.1_70b_Priestess_V1
8
- - migtissera/Tess-3-Llama-3.1-70B
9
  library_name: transformers
10
  tags:
11
  - mergekit
12
  - merge
 
 
13
 
14
  ---
 
 
 
15
  # about
16
 
17
  The base of Hexagon Purple V2, Smartracks, remains unchanged, and is a "3 levels" stock merge including Deepseek Distill R1 (3 flavors), Nemotron, and Tulu capabilities.
 
1
  ---
2
  base_model:
3
+ - Nexesenex/Llama_3.x_70b_Hexagon_Purple_V2
4
+ base_model_relation: quantized
 
 
 
 
5
  library_name: transformers
6
  tags:
7
  - mergekit
8
  - merge
9
+ - exl2
10
+ - 8-bit
11
 
12
  ---
13
+ # EXL2 Quant
14
+ This is an EXL2 Quant (8.0bpw H8) by ArtusDev.
15
+
16
  # about
17
 
18
  The base of Hexagon Purple V2, Smartracks, remains unchanged, and is a "3 levels" stock merge including Deepseek Distill R1 (3 flavors), Nemotron, and Tulu capabilities.