measurement.json

README.md

@@ -0,0 +1,96 @@
+---
+license: other
+license_name: llama3
+license_link: https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+  - llama-3
+datasets:
+- jondurbin/airoboros-3.2
+- bluemoon-fandom-1-1-rp-cleaned
+- boolq
+- LDJnr/Capybara
+- jondurbin/cinematika-v0.1
+- glaiveai/glaive-function-calling-v2
+- grimulkan/LimaRP-augmented
+- piqa
+- Vezora/Tested-22k-Python-Alpaca
+- mattpscott/airoboros-summarization
+- unalignment/toxic-dpo-v0.2
+- allenai/ultrafeedback_binarized_cleaned
+- argilla/distilabel-intel-orca-dpo-pairs
+- jondurbin/airoboros-3.2
+- jondurbin/contextual-dpo-v0.1
+- jondurbin/gutenberg-dpo-v0.1
+- jondurbin/py-dpo-v0.1
+- jondurbin/truthy-dpo-v0.1
+- jondurbin/gutenberg-dpo-v0.1
+- lmsys/lmsys-chat-1m
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+
+## Exllama v2 Quantizations of airoboros-dpo-70b-3.3
+
+Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.21">turboderp's ExLlamaV2 v0.0.21</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/jondurbin/airoboros-dpo-70b-3.3
+
+
+<a href="https://huggingface.co/bartowski/airoboros-dpo-70b-3.3-exl2/tree/6_5">6.5 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/airoboros-dpo-70b-3.3-exl2/tree/4_25">4.25 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/airoboros-dpo-70b-3.3-exl2/tree/3_5">3.5 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/airoboros-dpo-70b-3.3-exl2/tree/3_0">3.0 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/airoboros-dpo-70b-3.3-exl2/tree/2_5">2.5 bits per weight</a>
+
+<a href="https://huggingface.co/bartowski/airoboros-dpo-70b-3.3-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/airoboros-dpo-70b-3.3-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 `airoboros-dpo-70b-3.3-exl2`:
+
+```shell
+mkdir airoboros-dpo-70b-3.3-exl2
+huggingface-cli download bartowski/airoboros-dpo-70b-3.3-exl2 --local-dir airoboros-dpo-70b-3.3-exl2 --local-dir-use-symlinks False
+```
+
+To download from a different branch, add the `--revision` parameter:
+
+Linux:
+
+```shell
+mkdir airoboros-dpo-70b-3.3-exl2-6_5
+huggingface-cli download bartowski/airoboros-dpo-70b-3.3-exl2 --revision 6_5 --local-dir airoboros-dpo-70b-3.3-exl2-6_5 --local-dir-use-symlinks False
+```
+
+Windows (which apparently doesn't like _ in folders sometimes?):
+
+```shell
+mkdir airoboros-dpo-70b-3.3-exl2-6.5
+huggingface-cli download bartowski/airoboros-dpo-70b-3.3-exl2 --revision 6_5 --local-dir airoboros-dpo-70b-3.3-exl2-6.5 --local-dir-use-symlinks False
+```