Hugging Face's logo

bartowski
/
Phi-3-medium-4k-instruct-exl2

Text Generation
multilingual
nlp
code
Model card Files Community
1
bartowski commited on
Commit
1f5ce47
•
1 Parent(s): 58085a0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -40,7 +40,7 @@ Original model: https://huggingface.co/microsoft/Phi-3-medium-4k-instruct
40
  ## Available sizes
41
 
42
  | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | Description |
43
- | ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
44
  | [8_0](https://huggingface.co/bartowski/Phi-3-medium-4k-instruct-exl2/tree/8_0) | 8.0 | 8.0 | 14.0 GB | 16.4 GB | Max quality that ExLlamaV2 can produce, **recommended**. |
45
  | [6_5](https://huggingface.co/bartowski/Phi-3-medium-4k-instruct-exl2/tree/6_5) | 6.5 | 8.0 | 12.5 GB | 14.9 GB | Near unquantized performance at vastly reduced size, **recommended**. |
46
  | [5_0](https://huggingface.co/bartowski/Phi-3-medium-4k-instruct-exl2/tree/5_0) | 5.0 | 6.0 | 10.0 GB | 12.4 GB | Slightly lower quality vs 6.5. |
 
40
  ## Available sizes
41
 
42
  | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | Description |
43
+ | ----- | ---- | ------- | ------ | ------ | ------------ |
44
  | [8_0](https://huggingface.co/bartowski/Phi-3-medium-4k-instruct-exl2/tree/8_0) | 8.0 | 8.0 | 14.0 GB | 16.4 GB | Max quality that ExLlamaV2 can produce, **recommended**. |
45
  | [6_5](https://huggingface.co/bartowski/Phi-3-medium-4k-instruct-exl2/tree/6_5) | 6.5 | 8.0 | 12.5 GB | 14.9 GB | Near unquantized performance at vastly reduced size, **recommended**. |
46
  | [5_0](https://huggingface.co/bartowski/Phi-3-medium-4k-instruct-exl2/tree/5_0) | 5.0 | 6.0 | 10.0 GB | 12.4 GB | Slightly lower quality vs 6.5. |