|
|
--- |
|
|
base_model: google/medgemma-27b-it |
|
|
extra_gated_button_content: Acknowledge license |
|
|
extra_gated_heading: Access MedGemma on Hugging Face |
|
|
extra_gated_prompt: To access MedGemma on Hugging Face, you're required to review |
|
|
and agree to [Health AI Developer Foundation's terms of use](https://developers.google.com/health-ai-developer-foundations/terms). |
|
|
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: other |
|
|
license_link: https://developers.google.com/health-ai-developer-foundations/terms |
|
|
license_name: health-ai-developer-foundations |
|
|
mradermacher: |
|
|
readme_rev: 1 |
|
|
quantized_by: mradermacher |
|
|
tags: |
|
|
- medical |
|
|
- x-ray |
|
|
- pathology |
|
|
- dermatology |
|
|
- fundus |
|
|
- radiology report generation |
|
|
- chest-x-ray |
|
|
- medical-embeddings |
|
|
- image-classification |
|
|
- zero-shot-image-classification |
|
|
- image-feature-extraction |
|
|
- image-text-to-text |
|
|
--- |
|
|
## About |
|
|
|
|
|
<!-- ### quantize_version: 2 --> |
|
|
<!-- ### output_tensor_quantised: 1 --> |
|
|
<!-- ### convert_type: hf --> |
|
|
<!-- ### vocab_type: --> |
|
|
<!-- ### tags: nicoboss --> |
|
|
weighted/imatrix quants of https://huggingface.co/google/medgemma-27b-it |
|
|
|
|
|
<!-- provided-files --> |
|
|
|
|
|
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#medgemma-27b-it-i1-GGUF).*** |
|
|
|
|
|
static quants are available at https://huggingface.co/mradermacher/medgemma-27b-it-GGUF |
|
|
|
|
|
**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/medgemma-27b-it-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/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ1_S.gguf) | i1-IQ1_S | 6.4 | for the desperate | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ1_M.gguf) | i1-IQ1_M | 6.9 | mostly desperate | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.8 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ2_S.gguf) | i1-IQ2_S | 8.9 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ2_M.gguf) | i1-IQ2_M | 9.6 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q2_K_S.gguf) | i1-Q2_K_S | 9.9 | very low quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q2_K.gguf) | i1-Q2_K | 10.6 | IQ3_XXS probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.8 | lower quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q4_0.gguf) | i1-Q4_0 | 15.7 | fast, low quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.6 | fast, recommended | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q4_1.gguf) | i1-Q4_1 | 17.3 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q5_K_S.gguf) | i1-Q5_K_S | 18.9 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.4 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/medgemma-27b-it-i1-GGUF/resolve/main/medgemma-27b-it.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | practically like static Q6_K | |
|
|
|
|
|
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. |
|
|
|
|
|
<!-- end --> |
|
|
|
