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
weighted/imatrix quants of https://huggingface.co/ChuckMcSneed/dolphin-2.9.1-dbrx-llamacppfixed
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 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 | i1-IQ2_M | 43.3 | |
| GGUF | i1-Q2_K | 48.1 | IQ3_XXS probably better |
| PART 1 PART 2 | i1-IQ3_XXS | 50.8 | lower quality |
| PART 1 PART 2 | i1-Q3_K_S | 56.9 | IQ3_XS probably better |
| PART 1 PART 2 | i1-Q3_K_M | 63.3 | IQ3_S probably better |
| PART 1 PART 2 | i1-Q3_K_L | 68.5 | IQ3_M probably better |
| PART 1 PART 2 | i1-IQ4_XS | 70.2 | |
| PART 1 PART 2 | i1-Q4_K_S | 75.0 | optimal size/speed/quality |
| PART 1 PART 2 | i1-Q4_K_M | 80.0 | fast, recommended |
| PART 1 PART 2 | i1-Q5_K_S | 90.7 | |
| PART 1 PART 2 PART 3 | 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):
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, 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 hardware for calculating the imatrix for these quants.