83 lines
5.1 KiB
Markdown
83 lines
5.1 KiB
Markdown
---
|
||
base_model: mlabonne/Gemmalpaca-7B
|
||
datasets:
|
||
- vicgalle/alpaca-gpt4
|
||
extra_gated_button_content: Acknowledge license
|
||
extra_gated_heading: Access Gemma on Hugging Face
|
||
extra_gated_prompt: To access Gemma 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: other
|
||
license_link: https://ai.google.dev/gemma/terms
|
||
license_name: gemma-terms-of-use
|
||
quantized_by: mradermacher
|
||
---
|
||
## About
|
||
|
||
<!-- ### quantize_version: 2 -->
|
||
<!-- ### output_tensor_quantised: 1 -->
|
||
<!-- ### convert_type: hf -->
|
||
<!-- ### vocab_type: -->
|
||
<!-- ### tags: nicoboss -->
|
||
weighted/imatrix quants of https://huggingface.co/mlabonne/Gemmalpaca-7B
|
||
|
||
<!-- provided-files -->
|
||
static quants are available at https://huggingface.co/mradermacher/Gemmalpaca-7B-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/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.3 | for the desperate |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.7 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.9 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q2_K.gguf) | i1-Q2_K | 3.6 | IQ3_XXS probably better |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.6 | lower quality |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.9 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 4.1 | beats Q3_K* |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.1 | IQ3_XS probably better |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.5 | IQ3_S probably better |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.8 | IQ3_M probably better |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.9 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q4_0.gguf) | i1-Q4_0 | 5.1 | fast, low quality |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.1 | optimal size/speed/quality |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.4 | fast, recommended |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.1 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.2 | |
|
||
| [GGUF](https://huggingface.co/mradermacher/Gemmalpaca-7B-i1-GGUF/resolve/main/Gemmalpaca-7B.i1-Q6_K.gguf) | i1-Q6_K | 7.1 | 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 -->
|