Hugging Face's logo

R136a1
/
MythoMax-L2-13B-exl2

Text Generation
Transformers
English
llama
Inference Endpoints
Model card Files Community
2
R136a1 commited on
Commit
7c1e85e
•
1 Parent(s): 3e237f6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ Other quantized models are available from TheBloke: [GGML](https://huggingface.c
14
  | [main](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/main) | 5 | 6.1018 | Up to 6144 context size on T4 GPU |
15
  | [6bit](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/6bit) | 6 | 6.1182 | 4096 context size (tokens) on T4 GPU |
16
  | [3bit](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/3bit) | 3 | 6.3666 | Low bits quant while still good |
17
- | [4bit](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/4bit) | 4 | 6.1601 | To be updated |
18
  | - | 7 | 6.1056 | 2048 max context size for T4 GPU |
19
  | - | 8 | 6.1027 | Just, why? |
20
 
 
14
  | [main](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/main) | 5 | 6.1018 | Up to 6144 context size on T4 GPU |
15
  | [6bit](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/6bit) | 6 | 6.1182 | 4096 context size (tokens) on T4 GPU |
16
  | [3bit](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/3bit) | 3 | 6.3666 | Low bits quant while still good |
17
+ | [4bit](https://huggingface.co/R136a1/MythoMax-L2-13B-exl2/tree/4bit) | 4 | 6.1601 | Slightly better than 4bit GPTQ |
18
  | - | 7 | 6.1056 | 2048 max context size for T4 GPU |
19
  | - | 8 | 6.1027 | Just, why? |
20