mradermacher's picture
auto-patch README.md
f3c5cec verified
---
base_model: ChuckMcSneed/dolphin-2.9.1-dbrx-llamacppfixed
datasets:
- cognitivecomputations/Dolphin-2.9
- teknium/OpenHermes-2.5
- m-a-p/CodeFeedback-Filtered-Instruction
- cognitivecomputations/dolphin-coder
- cognitivecomputations/samantha-data
- microsoft/orca-math-word-problems-200k
- Locutusque/function-calling-chatml
- internlm/Agent-FLAN
language:
- en
library_name: transformers
license: other
license_link: https://www.databricks.com/legal/open-model-license
license_name: databricks-open-model-license
quantized_by: mradermacher
tags:
- generated_from_trainer
- axolotl
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/ChuckMcSneed/dolphin-2.9.1-dbrx-llamacppfixed
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-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/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ1_S.gguf) | i1-IQ1_S | 27.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ1_M.gguf) | i1-IQ1_M | 29.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 34.7 | |
| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ2_XS.gguf) | i1-IQ2_XS | 38.6 | |
| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ2_S.gguf) | i1-IQ2_S | 39.4 | |
| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ2_M.gguf) | i1-IQ2_M | 43.3 | |
| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q2_K.gguf) | i1-Q2_K | 48.1 | IQ3_XXS probably better |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ3_XXS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ3_XXS.gguf.part2of2) | i1-IQ3_XXS | 50.8 | lower quality |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 53.9 | |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 56.9 | beats Q3_K* |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 56.9 | IQ3_XS probably better |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 58.1 | |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 63.3 | IQ3_S probably better |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 68.5 | IQ3_M probably better |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 70.2 | |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 74.6 | fast, low quality |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 75.0 | optimal size/speed/quality |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 80.0 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 90.7 | |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 93.7 | |
| [PART 1](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/dolphin-2.9.1-dbrx-llamacppfixed-i1-GGUF/resolve/main/dolphin-2.9.1-dbrx-llamacppfixed.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 108.1 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
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 -->