Views
No views yet
| Branch | Bits | lm_head bits | Size (4k) | Size (16k) | Description |
|---|---|---|---|---|---|
| 8_0 | 8.0 | 8.0 | 9.4 GB | 15.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| 6_5 | 6.5 | 8.0 | 8.6 GB | 14.8 GB | Near unquantized performance at vastly reduced size, recommended. |
| 5_0 | 5.0 | 6.0 | 7.2 GB | 13.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards with 4k context. |
| 4_25 | 4.25 | 6.0 | 6.5 GB | 12.7 GB | GPTQ equivalent bits per weight. |
| 3_5 | 3.5 | 6.0 | 5.9 GB | 12.1 GB | Lower quality, not recommended. |
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/OpenCodeInterpreter-CL-7B-exl2 OpenCodeInterpreter-CL-7B-exl2-6_5pip3 install huggingface-hubmain (only useful if you only care about measurement.json) branch to a folder called OpenCodeInterpreter-CL-7B-exl2:1mkdir OpenCodeInterpreter-CL-7B-exl2
2huggingface-cli download bartowski/OpenCodeInterpreter-CL-7B-exl2 --local-dir OpenCodeInterpreter-CL-7B-exl2 --local-dir-use-symlinks False--revision parameter:1mkdir OpenCodeInterpreter-CL-7B-exl2-6_5
2huggingface-cli download bartowski/OpenCodeInterpreter-CL-7B-exl2 --revision 6_5 --local-dir OpenCodeInterpreter-CL-7B-exl2-6_5 --local-dir-use-symlinks False1mkdir OpenCodeInterpreter-CL-7B-exl2-6.5
2huggingface-cli download bartowski/OpenCodeInterpreter-CL-7B-exl2 --revision 6_5 --local-dir OpenCodeInterpreter-CL-7B-exl2-6.5 --local-dir-use-symlinks False