72 lines
4.8 KiB
Markdown
72 lines
4.8 KiB
Markdown
---
|
||
base_model: google/codegemma-7b
|
||
extra_gated_button_content: Acknowledge license
|
||
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.
|
||
language:
|
||
- en
|
||
library_name: transformers
|
||
license: gemma
|
||
license_link: https://ai.google.dev/gemma/terms
|
||
quantized_by: mradermacher
|
||
---
|
||
## About
|
||
|
||
<!-- ### quantize_version: 2 -->
|
||
<!-- ### output_tensor_quantised: 1 -->
|
||
<!-- ### convert_type: hf -->
|
||
<!-- ### vocab_type: -->
|
||
<!-- ### tags: -->
|
||
static quants of https://huggingface.co/google/codegemma-7b
|
||
|
||
<!-- provided-files -->
|
||
weighted/imatrix quants are available at https://huggingface.co/mradermacher/codegemma-7b-i1-GGUF
|
||
## Usage
|
||
|
||
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
||
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
|
||
more details, including on how to concatenate multi-part files.
|
||
|
||
## Provided Quants
|
||
|
||
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
||
|
||
| Link | Type | Size/GB | Notes |
|
||
|:-----|:-----|--------:|:------|
|
||
| [GGUF](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.1 | fast on arm, low quality |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q2_K.gguf) | Q2_K | 7.1 | |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q3_K_S.gguf) | Q3_K_S | 8.1 | |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q3_K_M.gguf) | Q3_K_M | 8.8 | lower quality |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q3_K_L.gguf) | Q3_K_L | 9.5 | |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.IQ4_XS.gguf) | IQ4_XS | 9.7 | |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q4_K_S.gguf) | Q4_K_S | 10.2 | fast, recommended |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q4_K_M.gguf) | Q4_K_M | 10.8 | fast, recommended |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q5_K_S.gguf) | Q5_K_S | 12.1 | |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q5_K_M.gguf) | Q5_K_M | 12.4 | |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q6_K.gguf) | Q6_K | 14.1 | very good quality |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.Q8_0.gguf) | Q8_0 | 18.3 | fast, best quality |
|
||
| [PART 1](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/CodeGemma-7b.f16.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-7b-GGUF/resolve/main/codegemma-7b.f16.gguf) | f16 | 34.3 | 16 bpw, overkill |
|
||
|
||
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
||
types (lower is better):
|
||
|
||
|
||
|
||
And here are Artefact2's thoughts on the matter:
|
||
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
|
||
|
||
## FAQ / Model Request
|
||
|
||
See https://huggingface.co/mradermacher/model_requests for some answers to
|
||
questions you might have and/or if you want some other model quantized.
|
||
|
||
## Thanks
|
||
|
||
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
|
||
me use its servers and providing upgrades to my workstation to enable
|
||
this work in my free time.
|
||
|
||
<!-- end -->
|