bartowski/Qwen2.5-Coder-7B-Instruct-exl2

Exllama v2 Quantizations of Qwen2.5-Coder-7B-Instruct

Using turboderp's ExLlamaV2 v0.2.2 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./Qwen/Qwen2.5-Coder-7B-Instruct

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

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/Qwen2.5-Coder-7B-Instruct-exl2 Qwen2.5-Coder-7B-Instruct-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/Qwen2.5-Coder-7B-Instruct-exl2 --revision 6_5 --local-dir Qwen2.5-Coder-7B-Instruct-exl2-6_5

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download bartowski/Qwen2.5-Coder-7B-Instruct-exl2 --revision 6_5 --local-dir Qwen2.5-Coder-7B-Instruct-exl2-6.5

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski