measurement.json

README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+extra_gated_heading: Access CodeGemma on Hugging Face
+extra_gated_prompt: >-
+  To access CodeGemma on Hugging Face, you’re required to review and agree to
+  Google’s usage license. To do this, please ensure you’re logged-in to Hugging
+  Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
+pipeline_tag: text-generation
+widget:
+- text: >
+    <start_of_turn>user
+    Write a Python function to calculate the nth fibonacci number.<end_of_turn>
+    <start_of_turn>model
+inference:
+  parameters:
+    max_new_tokens: 200
+license: gemma
+license_link: https://ai.google.dev/gemma/terms
+quantized_by: bartowski
+---
+
+## Exllama v2 Quantizations of codegemma-1.1-7b-it
+
+Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.20">turboderp's ExLlamaV2 v0.0.20</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.
+
+Original model: https://huggingface.co/google/codegemma-1.1-7b-it
+
+## Prompt format
+
+No chat template specified so default is used. This may be incorrect, check original model card for details.
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+## Available sizes
+
+No GQA - VRAM requirements will be higher
+
+| Branch                                                         | Bits | lm_head bits | Size (4k) | Size (16k) | Description |
+| -------------------------------------------------------------- | ---- | ------------ | --------- | ---------- | ----------- |
+| [8_0](https://huggingface.co/bartowski/codegemma-1.1-7b-it-exl2/tree/8_0) | 8.0 | 8.0 | 14.0 GB | 19.4 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
+| [6_5](https://huggingface.co/bartowski/codegemma-1.1-7b-it-exl2/tree/6_5) | 6.5  | 8.0 | 12.5 GB | 17.9 GB | Near unquantized performance at vastly reduced size, **recommended**. |
+| [5_0](https://huggingface.co/bartowski/codegemma-1.1-7b-it-exl2/tree/5_0) | 5.0  | 6.0 | 10.9 GB | 16.3 GB | Slightly lower quality vs 6.5, but usable on 8GB cards with 4k context. |
+| [4_25](https://huggingface.co/bartowski/codegemma-1.1-7b-it-exl2/tree/4_25) | 4.25 | 6.0 | 10.2 GB | 15.7 GB | GPTQ equivalent bits per weight. |
+| [3_5](https://huggingface.co/bartowski/codegemma-1.1-7b-it-exl2/tree/3_5) | 3.5 | 6.0 | 9.5 GB | 14.9 GB | Lower quality, not recommended. |
+
+## Download instructions
+
+With git:
+
+```shell
+git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/codegemma-1.1-7b-it-exl2 codegemma-1.1-7b-it-exl2-6_5
+```
+
+With huggingface hub (credit to TheBloke for instructions):
+
+```shell
+pip3 install huggingface-hub
+```
+
+To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
+
+Linux:
+
+```shell
+huggingface-cli download bartowski/codegemma-1.1-7b-it-exl2 --revision 6_5 --local-dir codegemma-1.1-7b-it-exl2-6_5 --local-dir-use-symlinks False
+```
+
+Windows (which apparently doesn't like _ in folders sometimes?):
+
+```shell
+huggingface-cli download bartowski/codegemma-1.1-7b-it-exl2 --revision 6_5 --local-dir codegemma-1.1-7b-it-exl2-6.5 --local-dir-use-symlinks False
+```
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski