bartowski commited on
Commit
9cc6157
1 Parent(s): 8940448

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -18,7 +18,9 @@ Original model: https://huggingface.co/migtissera/Tess-2.0-Yi-34B-200K
18
 
19
  | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
20
  | ------ | ---- | ------------ | ---- | ---- | ---- | ----------- |
 
21
  | [6_5](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/6_5) | 6.5 | 8.0 | 28.9 GB | 31.6 GB | 35.6 GB | Near unquantized performance at vastly reduced size, **recommended**. |
 
22
  | [4_25](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/4_25) | 4.25 | 6.0 | 19.5 GB | 22.2 GB | 26.2 GB | GPTQ equivalent bits per weight, slightly higher quality. |
23
  | [3_5](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/3_5) | 3.5 | 6.0 | 16.5 GB | 19.2 GB | 23.2 GB | Lower quality, only use if you have to. |
24
  | [3_0](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/3_0) | 3.0 | 6.0 | 14.3 GB | 17.0 GB | 21.0 GB | Very low quality, usable with 16gb of VRAM. |
 
18
 
19
  | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
20
  | ------ | ---- | ------------ | ---- | ---- | ---- | ----------- |
21
+ | [8_0](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/8_0) | 8.0 | 8.0 | 34.9 GB | 37.6 GB | 41.6 GB | Max quality producable by ExLlamav2, generally unneeded but maximum performance |
22
  | [6_5](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/6_5) | 6.5 | 8.0 | 28.9 GB | 31.6 GB | 35.6 GB | Near unquantized performance at vastly reduced size, **recommended**. |
23
+ | [5_0](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/5_0) | 5.0 | 8.0 | 22.6 GB | 25.3 GB | 29.3 GB | Very high quality, usable at 4k context on 24GB. |
24
  | [4_25](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/4_25) | 4.25 | 6.0 | 19.5 GB | 22.2 GB | 26.2 GB | GPTQ equivalent bits per weight, slightly higher quality. |
25
  | [3_5](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/3_5) | 3.5 | 6.0 | 16.5 GB | 19.2 GB | 23.2 GB | Lower quality, only use if you have to. |
26
  | [3_0](https://huggingface.co/bartowski/Tess-2.0-Yi-34B-200K-exl2/tree/3_0) | 3.0 | 6.0 | 14.3 GB | 17.0 GB | 21.0 GB | Very low quality, usable with 16gb of VRAM. |