Hugging Face's logo

DeusImperator
/
L3-8B-Stheno-v3.2_exl2_8.04bpw

Text Generation
Transformers
Safetensors
English
llama
conversational
text-generation-inference
Inference Endpoints
exl2
Model card Files Community
DeusImperator commited on
Commit
9795026
·
verified ·
1 Parent(s): e576dd8

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -9,11 +9,11 @@ datasets:
9
  - Sao10K/c2-Logs-Filtered
10
  ---
11
 
12
- # L3-8B-Stheno-v3.2 - EXL2 8bpw rpcal mk2
13
 
14
- This is a 8bpw EXL2 quant of [Sao10K/L3-8B-Stheno-v3.3](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2)
15
 
16
- This quant was made using exllamav2-0.0.21 with [Bluemoon-light dataset](https://huggingface.co/datasets/ParasiticRogue/Bluemoon-Light) for RP
17
 
18
  I tested this quant shortly in some random RPs (including one over 8k context - with RoPE scaling as recommended in webui) and it seems to work fine.
19
 
 
9
  - Sao10K/c2-Logs-Filtered
10
  ---
11
 
12
+ # L3-8B-Stheno-v3.2 - EXL2 8.04bpw
13
 
14
+ This is a 8bpw EXL2 quant of [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2)
15
 
16
+ This quant was made using exllamav2-0.0.21 with default dataset.
17
 
18
  I tested this quant shortly in some random RPs (including one over 8k context - with RoPE scaling as recommended in webui) and it seems to work fine.
19