Update Jan 27: This model was done before some config updates from internlm, please try the new one here and report any differences: https://huggingface.co/bartowski/internlm2-chat-7b-llama-exl2/

Exllama v2 Quantizations of internlm2-chat-7b-llama

Using turboderp's ExLlamaV2 v0.0.11 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/internlm/internlm2-chat-7b

Model Size: 7b

Branch	Bits	lm_head bits	Dataset	Size	Description
8_0	8.0	8.0	Default	9.8 GB	Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5	6.5	8.0	Default	8.6 GB	Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0	5.0	6.0	Default	7.4 GB	Slightly lower perplexity vs 6.5.
4_0	4.0	6.0	Default	6.5 GB	Just under GPTQ equivalent bits per weight.
3_5	3.5	6.0	Default	6.1 GB	Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/internlm2-chat-7b-llama-exl2-old

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download the main (only useful if you only care about measurement.json) branch to a folder called internlm2-chat-7b-llama-exl2:

mkdir internlm2-chat-7b-llama-exl2
huggingface-cli download bartowski/internlm2-chat-7b-llama-exl2-old --local-dir internlm2-chat-7b-llama-exl2 --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

mkdir internlm2-chat-7b-llama-exl2-6_5
huggingface-cli download bartowski/internlm2-chat-7b-llama-exl2-old --revision 6_5 --local-dir internlm2-chat-7b-llama-exl2-6_5 --local-dir-use-symlinks False