Views
No views yet
<|user|>
{prompt}<|end|>
<|assistant|>
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | Description |
|---|---|---|---|---|---|
| 8_0 | 8.0 | 8.0 | 14.0 GB | 16.4 GB | Max quality that ExLlamaV2 can produce, recommended. |
| 6_5 | 6.5 | 8.0 | 12.5 GB | 14.9 GB | Near unquantized performance at vastly reduced size, recommended. |
| 5_0 | 5.0 | 6.0 | 10.0 GB | 12.4 GB | Slightly lower quality vs 6.5. |
| 4_25 | 4.25 | 6.0 | 8.8 GB | 11.2 GB | GPTQ equivalent bits per weight. |
| 3_5 | 3.5 | 6.0 | 7.6 GB | 10.0 GB | Lower quality, not recommended. |
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Phi-3-medium-4k-instruct-exl2 Phi-3-medium-4k-instruct-exl2-6_5pip3 install huggingface-hub--revision parameter. For example, to download the 6.5 bpw branch:huggingface-cli download bartowski/Phi-3-medium-4k-instruct-exl2 --revision 6_5 --local-dir Phi-3-medium-4k-instruct-exl2-6_5huggingface-cli download bartowski/Phi-3-medium-4k-instruct-exl2 --revision 6_5 --local-dir Phi-3-medium-4k-instruct-exl2-6.5