Main branch

README.md

@@ -0,0 +1,62 @@
+---
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+model-index:
+- name: WizardCoder
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      type: openai_humaneval
+      name: HumanEval
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 0.799
+      verified: false
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+
+## Exllama v2 Quantizations of WizardCoder-33B-V1.1
+
+Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization.
+
+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/WizardLM/WizardCoder-33B-V1.1
+
+## Download instructions
+
+With git:
+
+```shell
+git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/WizardCoder-33B-V1.1-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 `WizardCoder-33B-V1.1-exl2`:
+
+```shell
+mkdir WizardCoder-33B-V1.1-exl2
+huggingface-cli download bartowski/WizardCoder-33B-V1.1-exl2 --local-dir WizardCoder-33B-V1.1-exl2 --local-dir-use-symlinks False
+```
+
+To download from a different branch, add the `--revision` parameter:
+
+```shell
+mkdir WizardCoder-33B-V1.1-exl2
+huggingface-cli download bartowski/WizardCoder-33B-V1.1-exl2 --revision 4_0 --local-dir WizardCoder-33B-V1.1-exl2 --local-dir-use-symlinks False
+```