120 lines
4.0 KiB
Markdown
120 lines
4.0 KiB
Markdown
---
|
|
base_model: ATH-MaaS/Marco-Nano-Base
|
|
datasets:
|
|
- nvidia/Nemotron-CC-v2
|
|
- nvidia/Nemotron-Pretraining-SFT-v1
|
|
- nvidia/Nemotron-Pretraining-Specialized-v1
|
|
- nvidia/Nemotron-CC-v2.1
|
|
- allenai/dolmino-mix-1124
|
|
- nvidia/Nemotron-CC-Math-v1
|
|
- nvidia/OpenMathInstruct-2
|
|
- HuggingFaceTB/finemath
|
|
- LLM360/MegaMath
|
|
- open-thoughts/OpenThoughts3-1.2M
|
|
- opencsg/Fineweb-Edu-Chinese-V2.1
|
|
- HuggingFaceFW/fineweb-2
|
|
- allenai/dolma3_dolmino_mix-100B-1125
|
|
language:
|
|
- en
|
|
- zh
|
|
- ar
|
|
- de
|
|
- es
|
|
- fr
|
|
- ko
|
|
- ja
|
|
- pt
|
|
- tr
|
|
- id
|
|
- it
|
|
- nl
|
|
- pl
|
|
- ru
|
|
- vi
|
|
- th
|
|
- he
|
|
- uk
|
|
- ms
|
|
- bn
|
|
- cs
|
|
- ur
|
|
- kk
|
|
- el
|
|
- ro
|
|
- hu
|
|
- ne
|
|
- az
|
|
library_name: transformers
|
|
license: apache-2.0
|
|
mradermacher:
|
|
readme_rev: 1
|
|
quantized_by: mradermacher
|
|
tags:
|
|
- moe
|
|
- mixture-of-experts
|
|
- multilingual
|
|
- upcycling
|
|
---
|
|
## About
|
|
|
|
<!-- ### quantize_version: 2 -->
|
|
<!-- ### output_tensor_quantised: 1 -->
|
|
<!-- ### convert_type: hf -->
|
|
<!-- ### vocab_type: -->
|
|
<!-- ### tags: -->
|
|
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
|
|
<!-- ### quants_skip: -->
|
|
<!-- ### skip_mmproj: -->
|
|
static quants of https://huggingface.co/ATH-MaaS/Marco-Nano-Base
|
|
|
|
<!-- provided-files -->
|
|
|
|
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Marco-Nano-Base-GGUF).***
|
|
|
|
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Marco-Nano-Base-i1-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/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q2_K.gguf) | Q2_K | 3.5 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q3_K_S.gguf) | Q3_K_S | 4.0 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q3_K_L.gguf) | Q3_K_L | 4.5 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q4_K_M.gguf) | Q4_K_M | 5.6 | fast, recommended |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q5_K_S.gguf) | Q5_K_S | 5.9 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q5_K_M.gguf) | Q5_K_M | 6.3 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q6_K.gguf) | Q6_K | 7.4 | very good quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Base-GGUF/resolve/main/Marco-Nano-Base.f16.gguf) | f16 | 16.4 | 16 bpw, overkill |
|
|
|
|
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.
|
|
|
|
<!-- end -->
|