Compare commits
10 Commits
9c56dba1e9
...
77301c2a8c
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
77301c2a8c | ||
|
|
101a11aed5 | ||
|
|
781ad5e916 | ||
|
|
823a70558d | ||
|
|
b47c68cf91 | ||
|
|
acbefc111e | ||
|
|
7d24ca6340 | ||
|
|
cd4ea064ed | ||
|
|
a2d7d33c61 | ||
|
|
406366740d |
6
.gitattributes
vendored
6
.gitattributes
vendored
@@ -41,3 +41,9 @@ Fantastica-7b-Instruct-0.2-Italian_merged.Q2_K.gguf filter=lfs diff=lfs merge=lf
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Fantastica-7b-Instruct-0.2-Italian_merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
3
Fantastica-7b-Instruct-0.2-Italian_merged.IQ3_XS.gguf
Normal file
3
Fantastica-7b-Instruct-0.2-Italian_merged.IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4eb0ce211407788d93cb67c9d0318223ad63d60fd39a76984c2a8fcf8412e9d7
|
||||
size 3018815776
|
||||
3
Fantastica-7b-Instruct-0.2-Italian_merged.IQ4_XS.gguf
Normal file
3
Fantastica-7b-Instruct-0.2-Italian_merged.IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:54e988eb1c694303d5e7b1f28f790e76e6b4b98fae8edecbe8d90999018c18f4
|
||||
size 3944388896
|
||||
3
Fantastica-7b-Instruct-0.2-Italian_merged.Q3_K_L.gguf
Normal file
3
Fantastica-7b-Instruct-0.2-Italian_merged.Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:05b37dccb0319b8ff0ed107abb2eac9f2cb99b78a8f04c1387a3da4f1831c5ef
|
||||
size 3822024992
|
||||
3
Fantastica-7b-Instruct-0.2-Italian_merged.Q4_K_M.gguf
Normal file
3
Fantastica-7b-Instruct-0.2-Italian_merged.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9fd1bd0f2ac569932c5bae0fbfab6af51ce3b132282ef9bce18e7f02b488f2cb
|
||||
size 4368439584
|
||||
3
Fantastica-7b-Instruct-0.2-Italian_merged.Q5_K_M.gguf
Normal file
3
Fantastica-7b-Instruct-0.2-Italian_merged.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:35b2abe7ae538a2067dc1a54fc081beab86e7f44a9d680658b64876b2412b9b8
|
||||
size 5131409696
|
||||
3
Fantastica-7b-Instruct-0.2-Italian_merged.Q5_K_S.gguf
Normal file
3
Fantastica-7b-Instruct-0.2-Italian_merged.Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:045d073bfc94c104043430ff3a4d4664cbdc249e08f38a831f192ec641cdeb11
|
||||
size 4997716256
|
||||
32
README.md
32
README.md
@@ -1,9 +1,21 @@
|
||||
---
|
||||
exported_from: scribis/Fantastica-7b-Instruct-0.2-Italian_merged
|
||||
base_model: scribis/Fantastica-7b-Instruct-0.2-Italian_merged
|
||||
datasets:
|
||||
- scribis/Wikipedia_it_Trame_Romanzi
|
||||
- scribis/Corpus-Frasi-da-Opere-Letterarie
|
||||
- scribis/Wikipedia-it-Trame-di-Film
|
||||
- scribis/Wikipedia-it-Descrizioni-di-Dipinti
|
||||
- scribis/Wikipedia-it-Mitologia-Greca
|
||||
language:
|
||||
- en
|
||||
- it
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
quantized_by: mradermacher
|
||||
tags:
|
||||
- Italian
|
||||
- Mistral
|
||||
- finetuning
|
||||
- Text Generation
|
||||
---
|
||||
## About
|
||||
|
||||
@@ -13,7 +25,6 @@ quantized_by: mradermacher
|
||||
<!-- ### 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
|
||||
@@ -29,12 +40,20 @@ more details, including on how to concatenate multi-part files.
|
||||
| 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):
|
||||
|
||||
@@ -43,6 +62,11 @@ 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
|
||||
|
||||
Reference in New Issue
Block a user