Commit
•
4aadafb
1
Parent(s):
d7d4931
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
<!-- ### quantize_version: 2 -->
|
| 2 |
<!-- ### output_tensor_quantised: 1 -->
|
| 3 |
<!-- ### convert_type: hf -->
|
| 4 |
<!-- ### vocab_type: -->
|
| 5 |
static quants of https://huggingface.co/CohereForAI/aya-23-35B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: CohereForAI/aya-23-35B
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- fr
|
| 6 |
+
- de
|
| 7 |
+
- es
|
| 8 |
+
- it
|
| 9 |
+
- pt
|
| 10 |
+
- ja
|
| 11 |
+
- ko
|
| 12 |
+
- zh
|
| 13 |
+
- ar
|
| 14 |
+
- el
|
| 15 |
+
- fa
|
| 16 |
+
- pl
|
| 17 |
+
- id
|
| 18 |
+
- cs
|
| 19 |
+
- he
|
| 20 |
+
- hi
|
| 21 |
+
- nl
|
| 22 |
+
- ro
|
| 23 |
+
- ru
|
| 24 |
+
- tr
|
| 25 |
+
- uk
|
| 26 |
+
- vi
|
| 27 |
+
library_name: transformers
|
| 28 |
+
license: cc-by-nc-4.0
|
| 29 |
+
quantized_by: mradermacher
|
| 30 |
+
---
|
| 31 |
+
## About
|
| 32 |
+
|
| 33 |
<!-- ### quantize_version: 2 -->
|
| 34 |
<!-- ### output_tensor_quantised: 1 -->
|
| 35 |
<!-- ### convert_type: hf -->
|
| 36 |
<!-- ### vocab_type: -->
|
| 37 |
static quants of https://huggingface.co/CohereForAI/aya-23-35B
|
| 38 |
+
|
| 39 |
+
<!-- provided-files -->
|
| 40 |
+
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.
|
| 41 |
+
## Usage
|
| 42 |
+
|
| 43 |
+
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
| 44 |
+
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
|
| 45 |
+
more details, including on how to concatenate multi-part files.
|
| 46 |
+
|
| 47 |
+
## Provided Quants
|
| 48 |
+
|
| 49 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 50 |
+
|
| 51 |
+
| Link | Type | Size/GB | Notes |
|
| 52 |
+
|:-----|:-----|--------:|:------|
|
| 53 |
+
| [GGUF](https://huggingface.co/mradermacher/aya-23-35B-GGUF/resolve/main/aya-23-35B.IQ3_S.gguf) | IQ3_S | 16.0 | beats Q3_K* |
|
| 54 |
+
| [GGUF](https://huggingface.co/mradermacher/aya-23-35B-GGUF/resolve/main/aya-23-35B.Q4_K_S.gguf) | Q4_K_S | 20.5 | fast, recommended |
|
| 55 |
+
| [GGUF](https://huggingface.co/mradermacher/aya-23-35B-GGUF/resolve/main/aya-23-35B.Q8_0.gguf) | Q8_0 | 37.3 | fast, best quality |
|
| 56 |
+
|
| 57 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 58 |
+
types (lower is better):
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
And here are Artefact2's thoughts on the matter:
|
| 63 |
+
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
|
| 64 |
+
|
| 65 |
+
## FAQ / Model Request
|
| 66 |
+
|
| 67 |
+
See https://huggingface.co/mradermacher/model_requests for some answers to
|
| 68 |
+
questions you might have and/or if you want some other model quantized.
|
| 69 |
+
|
| 70 |
+
## Thanks
|
| 71 |
+
|
| 72 |
+
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
|
| 73 |
+
me use its servers and providing upgrades to my workstation to enable
|
| 74 |
+
this work in my free time.
|
| 75 |
+
|
| 76 |
+
<!-- end -->
|