Exllama v2 Quantizations of Replete-LLM-Qwen2-7b
Using turboderp's ExLlamaV2 v0.1.8 for quantization.
The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Original model: https://huggingface.co/Replete-AI/Replete-LLM-Qwen2-7b
Prompt format
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<|endoftext|>
Available sizes
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|---|---|---|---|---|---|---|
| 8_0 | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| 6_5 | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, recommended. |
| 5_0 | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| 4_25 | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| 3_5 | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Replete-LLM-Qwen2-7b-exl2 Replete-LLM-Qwen2-7b-exl2-6_5
With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hub
To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:
Linux:
huggingface-cli download bartowski/Replete-LLM-Qwen2-7b-exl2 --revision 6_5 --local-dir Replete-LLM-Qwen2-7b-exl2-6_5
Windows (which apparently doesn't like _ in folders sometimes?):
huggingface-cli download bartowski/Replete-LLM-Qwen2-7b-exl2 --revision 6_5 --local-dir Replete-LLM-Qwen2-7b-exl2-6.5
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski