bartowski commited on
Commit
31d8557
1 Parent(s): f01baa2

Update VRAM table

Browse files
Files changed (1) hide show
  1. README.md +7 -15
README.md CHANGED
@@ -23,23 +23,15 @@ Using <a href="https://github.com/turboderp/exllamav2/">turboderp's ExLlamaV2 v0
23
 
24
  Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
25
 
26
- Conversion was done using the default calibration dataset.
27
-
28
- Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
29
-
30
  Original model: https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b
31
 
32
-
33
- <a href="https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/8_0">8.0 bits per weight</a>
34
-
35
- <a href="https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/6_5">6.5 bits per weight</a>
36
-
37
- <a href="https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/5_0">5.0 bits per weight</a>
38
-
39
- <a href="https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/4_25">4.25 bits per weight</a>
40
-
41
- <a href="https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/3_5">3.5 bits per weight</a>
42
-
43
 
44
  ## Download instructions
45
 
 
23
 
24
  Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
25
 
 
 
 
 
26
  Original model: https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b
27
 
28
+ | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
29
+ | ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
30
+ | [8_0](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/8_0) | 8.0 | 8.0 | 16.6 GB | 17.5 GB | 18.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
31
+ | [6_5](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/6_5) | 6.5 | 8.0 | 13.9 GB | 14.9 GB | 16.2 GB | Near unquantized performance at vastly reduced size, **recommended**. |
32
+ | [5_0](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/5_0) | 5.0 | 6.0 | 11.2 GB | 12.2 GB | 13.5 GB | Slightly lower quality vs 6.5. |
33
+ | [4_25](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/4_25) | 4.25 | 6.0 | 9.8 GB | 10.7 GB | 12.0 GB | GPTQ equivalent bits per weight. |
34
+ | [3_5](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2/tree/3_5) | 3.5 | 6.0 | 8.4 GB | 9.3 GB | 10.6 GB | Lower quality, not recommended. |
 
 
 
 
35
 
36
  ## Download instructions
37