measurement.json

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct/blob/main/LICENSE
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-Coder-32B
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- code
+- codeqwen
+- chat
+- qwen
+- qwen-coder
+quantized_by: bartowski
+---
+
+## Exllama v2 Quantizations of Qwen2.5-Coder-32B-Instruct
+
+Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.2.3">turboderp's ExLlamaV2 v0.2.3</a> for quantization.
+
+<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
+
+Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
+
+Conversion was done using the default calibration dataset.
+
+Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
+
+Original model: https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct
+
+
+<a href="https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-exl2/tree/8_0">8.0 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-exl2/tree/6_5">6.5 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-exl2/tree/5_0">5.0 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-exl2/tree/4_25">4.25 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-exl2/tree/3_5">3.5 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-exl2/tree/3_0">3.0 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-exl2/tree/2_2">2.2 bits per weight</a>
+
+
+## Download instructions
+
+With git:
+
+```shell
+git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Qwen2.5-Coder-32B-Instruct-exl2
+```
+
+With huggingface hub (credit to TheBloke for instructions):
+
+```shell
+pip3 install huggingface-hub
+```
+
+To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Qwen2.5-Coder-32B-Instruct-exl2`:
+
+```shell
+mkdir Qwen2.5-Coder-32B-Instruct-exl2
+huggingface-cli download bartowski/Qwen2.5-Coder-32B-Instruct-exl2 --local-dir Qwen2.5-Coder-32B-Instruct-exl2
+```
+
+To download from a different branch, add the `--revision` parameter:
+
+Linux:
+
+```shell
+mkdir Qwen2.5-Coder-32B-Instruct-exl2-6_5
+huggingface-cli download bartowski/Qwen2.5-Coder-32B-Instruct-exl2 --revision 6_5 --local-dir Qwen2.5-Coder-32B-Instruct-exl2-6_5
+```
+
+Windows (which apparently doesn't like _ in folders sometimes?):
+
+```shell
+mkdir Qwen2.5-Coder-32B-Instruct-exl2-6.5
+huggingface-cli download bartowski/Qwen2.5-Coder-32B-Instruct-exl2 --revision 6_5 --local-dir Qwen2.5-Coder-32B-Instruct-exl2-6.5
+```