metadata
base_model: 01-ai/Yi-34B
datasets:
- teknium/OpenHermes-2.5
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- yi
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
About
weighted/imatrix quants of https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B
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 | 12.5 | |
| GGUF | i1-Q2_K | 13.5 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 14.0 | fast, lower quality |
| GGUF | i1-IQ3_XS | 14.8 | |
| GGUF | i1-Q3_K_S | 15.6 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 15.7 | fast, beats Q3_K* |
| GGUF | i1-Q3_K_M | 17.3 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 18.8 | IQ3_M probably better |
| GGUF | i1-Q4_K_S | 20.2 | almost as good as Q4_K_M |
| GGUF | i1-Q4_K_M | 21.3 | fast, medium quality |
| GGUF | i1-Q5_K_S | 24.3 | |
| GGUF | i1-Q5_K_M | 25.0 | best weighted quant |
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