π Model Description
base_model: internlm/OREAL-7B datasets:
- internlm/OREAL-RL-Prompts
- en
About
weighted/imatrix quants of https://huggingface.co/internlm/OREAL-7B
static quants are available at https://huggingface.co/mradermacher/OREAL-7B-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-IQ1_S | 2.0 | for the desperate |
GGUF | i1-IQ1_M | 2.1 | mostly desperate |
GGUF | i1-IQ2_XXS | 2.4 | |
GGUF | i1-IQ2_XS | 2.6 | |
GGUF | i1-IQ2_S | 2.7 | |
GGUF | i1-IQ2_M | 2.9 | |
GGUF | i1-Q2K_S | 2.9 | very low quality |
GGUF | i1-Q2K | 3.1 | IQ3XXS probably better |
GGUF | i1-IQ3_XXS | 3.2 | lower quality |
GGUF | i1-IQ3_XS | 3.4 | |
GGUF | i1-Q3KS | 3.6 | IQ3XS probably better |
GGUF | i1-IQ3S | 3.6 | beats Q3K* |
GGUF | i1-IQ3_M | 3.7 | |
GGUF | i1-Q3KM | 3.9 | IQ3S probably better |
GGUF | i1-Q3KL | 4.2 | IQ3M probably better |
GGUF | i1-IQ4_XS | 4.3 | |
GGUF | i1-IQ4NL | 4.5 | prefer IQ4XS |
GGUF | i1-Q4_0 | 4.5 | fast, low quality |
GGUF | i1-Q4K_S | 4.6 | optimal size/speed/quality |
GGUF | i1-Q4K_M | 4.8 | fast, recommended |
GGUF | i1-Q4_1 | 5.0 | |
GGUF | i1-Q5K_S | 5.4 | |
GGUF | i1-Q5K_M | 5.5 | |
GGUF | i1-Q6K | 6.4 | practically like static Q6K |
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 private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
π GGUF File List
π Filename | π¦ Size | β‘ Download |
---|---|---|
OREAL-7B.i1-IQ1_M.gguf
LFS
|
1.9 GB | Download |
OREAL-7B.i1-IQ1_S.gguf
LFS
|
1.77 GB | Download |
OREAL-7B.i1-IQ2_M.gguf
LFS
Q2
|
2.59 GB | Download |
OREAL-7B.i1-IQ2_S.gguf
LFS
Q2
|
2.42 GB | Download |
OREAL-7B.i1-IQ2_XS.gguf
LFS
Q2
|
2.3 GB | Download |
OREAL-7B.i1-IQ2_XXS.gguf
LFS
Q2
|
2.12 GB | Download |
OREAL-7B.i1-IQ3_M.gguf
LFS
Q3
|
3.33 GB | Download |
OREAL-7B.i1-IQ3_S.gguf
LFS
Q3
|
3.26 GB | Download |
OREAL-7B.i1-IQ3_XS.gguf
LFS
Q3
|
3.12 GB | Download |
OREAL-7B.i1-IQ3_XXS.gguf
LFS
Q3
|
2.9 GB | Download |
OREAL-7B.i1-IQ4_NL.gguf
LFS
Q4
|
4.13 GB | Download |
OREAL-7B.i1-IQ4_XS.gguf
LFS
Q4
|
3.93 GB | Download |
OREAL-7B.i1-Q2_K.gguf
LFS
Q2
|
2.81 GB | Download |
OREAL-7B.i1-Q2_K_S.gguf
LFS
Q2
|
2.64 GB | Download |
OREAL-7B.i1-Q3_K_L.gguf
LFS
Q3
|
3.81 GB | Download |
OREAL-7B.i1-Q3_K_M.gguf
LFS
Q3
|
3.55 GB | Download |
OREAL-7B.i1-Q3_K_S.gguf
LFS
Q3
|
3.25 GB | Download |
OREAL-7B.i1-Q4_0.gguf
Recommended
LFS
Q4
|
4.14 GB | Download |
OREAL-7B.i1-Q4_1.gguf
LFS
Q4
|
4.54 GB | Download |
OREAL-7B.i1-Q4_K_M.gguf
LFS
Q4
|
4.36 GB | Download |
OREAL-7B.i1-Q4_K_S.gguf
LFS
Q4
|
4.15 GB | Download |
OREAL-7B.i1-Q5_K_M.gguf
LFS
Q5
|
5.07 GB | Download |
OREAL-7B.i1-Q5_K_S.gguf
LFS
Q5
|
4.95 GB | Download |
OREAL-7B.i1-Q6_K.gguf
LFS
Q6
|
5.82 GB | Download |