Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
For a convenient overview and download list, visit our model page for this model.
Source du modèle
Description de la source
weighted/imatrix quants of https://huggingface.co/mkd-hossain/Keural-MoE-Pro-v1.0
For a convenient overview and download list, visit our model page for this model.
static quants are available at
Sources
1 sourceVérifié 22 sept.
Artefacts du modèle
15 artefactsKeural-MoE-Pro-v1.0.i1-IQ3_M.gguf
gguf · 14,7 GB · SHA-256 3cf9647b1125…06dd · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-IQ3_S.gguf
gguf · 14,5 GB · SHA-256 8dfd510903ef…d53b · Hugging Face
TéléchargerExtraits de sources
2 extraitsThis is a vision model - mmproj files (if any) will be in the static repository.
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | imatrix | 0.3 | imatrix file (for creating your own quants) |
| GGUF | i1-Q2_K | 13.3 | IQ3_XXS probably better |
| GGUF | i1-Q3_K_S | 15.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 15.7 | beats Q3_K* |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
image.png
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @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.
Keural-MoE-Pro-v1.0.i1-IQ4_XS.gguf
gguf · 17,9 GB · SHA-256 0999ce803393…f6de · Hugging Face
Keural-MoE-Pro-v1.0.i1-Q2_K.gguf
gguf · 12,3 GB · SHA-256 e95c62827779…8142 · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q3_K_L.gguf
gguf · 17,3 GB · SHA-256 927cfe1e3b09…352d · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q3_K_M.gguf
gguf · 16,0 GB · SHA-256 18d3d9d5aafd…b29f · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q3_K_S.gguf
gguf · 14,5 GB · SHA-256 da23869fcefb…59a2 · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q4_0.gguf
gguf · 18,9 GB · SHA-256 5e2f9a64e10b…cfa2 · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q4_1.gguf
gguf · 20,8 GB · SHA-256 e59ab3700b95…a00f · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q4_K_M.gguf
gguf · 20,2 GB · SHA-256 c3928d313f3c…a03a · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q4_K_S.gguf
gguf · 19,0 GB · SHA-256 34f20e43aca4…9d7a · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q5_K_M.gguf
gguf · 23,6 GB · SHA-256 777383100e03…8aeb · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q5_K_S.gguf
gguf · 22,9 GB · SHA-256 876ac6fc0a78…4f28 · Hugging Face
TéléchargerKeural-MoE-Pro-v1.0.i1-Q6_K.gguf
gguf · 27,2 GB · SHA-256 abe6c7a11167…6d74 · Hugging Face
Télécharger--- base_model: mkd-hossain/Keural-MoE-Pro-v1.0 language: - ko - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - korean - moe - lora - instruction-tuning - keural --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> weighted/imatrix quants of https://huggingface.co/mkd-hossain/Keural-MoE-Pro-v1.0 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Keural-MoE-Pro-v1.0-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Keural-MoE-Pro-v1.0-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Keural-MoE-Pro-v1.0-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/Keural-MoE-Pro-v1.0-i1-GGUF/resolve/main/Keural-MoE-Pro-v1.0.imatrix.gguf) | imatrix | 0.3 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Keural-MoE-Pro-v1.0-i1-GGUF/resolve/main/Keural-MoE-Pro-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 13.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Keural-MoE-Pro-v1.0-i1-GGUF/resolve/main/Keural-MoE-Pro-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.6 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Keural-MoE-Pro-v1.0-i1-GGUF/resolve/main/Keural-MoE-Pro-v1.0.i1-IQ3_S.gguf) | i1-IQ3_S | 15.7 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Keural-MoE-Pro-v1.0-i1-GGUF/resolve/main/Keural-MoE-Pro-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 15.9 | | | [GGUF](https://huggingface.co/mraderm...
Source context: 373 downloads · 0 likes · Library transformers · Repo mradermacher/Keural-MoE-Pro-v1.0-i1-GGUF
| i1-IQ3_M |
| 15.9 |
| GGUF | i1-Q3_K_M | 17.3 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 18.7 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 19.3 |
| GGUF | i1-Q4_0 | 20.4 | fast, low quality |
| GGUF | i1-Q4_K_S | 20.5 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 21.8 | fast, recommended |
| GGUF | i1-Q4_1 | 22.5 |
| GGUF | i1-Q5_K_S | 24.7 |
| GGUF | i1-Q5_K_M | 25.4 |
| GGUF | i1-Q6_K | 29.3 | practically like static Q6_K |
