72 lines
4.3 KiB
Markdown
72 lines
4.3 KiB
Markdown
---
|
|
datasets:
|
|
- scribis/Wikipedia_it_Trame_Romanzi
|
|
- scribis/Corpus-Frasi-da-Opere-Letterarie
|
|
- scribis/Wikipedia-it-Trame-di-Film
|
|
- scribis/Wikipedia-it-Descrizioni-di-Dipinti
|
|
exported_from: scribis/Fantastica-7b-Instruct-0.2-Italian_merged
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
license: apache-2.0
|
|
quantized_by: mradermacher
|
|
tags:
|
|
- Italian
|
|
- Mistral
|
|
- finetuning
|
|
- Text Generation
|
|
---
|
|
## About
|
|
|
|
<!-- ### quantize_version: 1 -->
|
|
<!-- ### output_tensor_quantised: 1 -->
|
|
<!-- ### convert_type: -->
|
|
<!-- ### vocab_type: -->
|
|
static quants of https://huggingface.co/scribis/Fantastica-7b-Instruct-0.2-Italian_merged
|
|
|
|
<!-- provided-files -->
|
|
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
|
|
## 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/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q2_K.gguf) | Q2_K | 2.8 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.IQ3_M.gguf) | IQ3_M | 3.4 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
|
|
| [GGUF](https://huggingface.co/mradermacher/Fantastica-7b-Instruct-0.2-Italian_merged-GGUF/resolve/main/Fantastica-7b-Instruct-0.2-Italian_merged.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
|
|
|
|
|
|
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
|
|
|
|
## 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 -->
|