|
|
--- |
|
|
base_model: allura-org/Q3-30B-A3B-Designant |
|
|
datasets: |
|
|
- PygmalionAI/PIPPA |
|
|
- Alfitaria/nemotron-ultra-reasoning-synthkink |
|
|
- PocketDoc/Dans-Prosemaxx-Gutenberg |
|
|
- FreedomIntelligence/Medical-R1-Distill-Data |
|
|
- cognitivecomputations/SystemChat-2.0 |
|
|
- allenai/tulu-3-sft-personas-instruction-following |
|
|
- kalomaze/Opus_Instruct_25k |
|
|
- simplescaling/s1K-claude-3-7-sonnet |
|
|
- ai2-adapt-dev/flan_v2_converted |
|
|
- grimulkan/theory-of-mind |
|
|
- grimulkan/physical-reasoning |
|
|
- nvidia/HelpSteer3 |
|
|
- nbeerbower/gutenberg2-dpo |
|
|
- nbeerbower/gutenberg-moderne-dpo |
|
|
- nbeerbower/Purpura-DPO |
|
|
- antiven0m/physical-reasoning-dpo |
|
|
- allenai/tulu-3-IF-augmented-on-policy-70b |
|
|
- NobodyExistsOnTheInternet/system-message-DPO |
|
|
language: |
|
|
- en |
|
|
library_name: transformers |
|
|
mradermacher: |
|
|
readme_rev: 1 |
|
|
quantized_by: mradermacher |
|
|
tags: |
|
|
- mergekit |
|
|
- axolotl |
|
|
- unsloth |
|
|
- roleplay |
|
|
- conversational |
|
|
--- |
|
|
## About |
|
|
|
|
|
<!-- ### quantize_version: 2 --> |
|
|
<!-- ### output_tensor_quantised: 1 --> |
|
|
<!-- ### convert_type: hf --> |
|
|
<!-- ### vocab_type: --> |
|
|
<!-- ### tags: nicoboss --> |
|
|
weighted/imatrix quants of https://huggingface.co/allura-org/Q3-30B-A3B-Designant |
|
|
|
|
|
<!-- provided-files --> |
|
|
|
|
|
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Q3-30B-A3B-Designant-i1-GGUF).*** |
|
|
|
|
|
static quants are available at https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-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/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 11.9 | lower quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.7 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-IQ3_S.gguf) | i1-IQ3_S | 13.4 | beats Q3_K* | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q4_0.gguf) | i1-Q4_0 | 17.5 | fast, low quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q4_1.gguf) | i1-Q4_1 | 19.3 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q5_K_M.gguf) | i1-Q5_K_M | 21.8 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Q3-30B-A3B-Designant-i1-GGUF/resolve/main/Q3-30B-A3B-Designant.i1-Q6_K.gguf) | i1-Q6_K | 25.2 | 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 --> |
|
|
|
