andrijdavid
commited on
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
@@ -29,6 +29,7 @@ license: cc-by-nc-4.0
|
|
29 |
library_name: transformers
|
30 |
tags:
|
31 |
- GGUF
|
|
|
32 |
quantized_by: andrijdavid
|
33 |
---
|
34 |
# aya-23-8B-GGUF
|
@@ -228,6 +229,10 @@ Here are guides on using llama-cpp-python and ctransformers with LangChain:
|
|
228 |
|
229 |
# Model Card for Aya-23-8B
|
230 |
|
|
|
|
|
|
|
|
|
231 |
## Model Summary
|
232 |
|
233 |
Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. Aya 23 focuses on pairing a highly performant pre-trained [Command family](https://huggingface.co/CohereForAI/c4ai-command-r-plus) of models with the recently released [Aya Collection](https://huggingface.co/datasets/CohereForAI/aya_collection). The result is a powerful multilingual large language model serving 23 languages.
|
@@ -243,10 +248,6 @@ Developed by: [Cohere For AI](https://cohere.for.ai) and [Cohere](https://cohere
|
|
243 |
- Model: aya-23-8B
|
244 |
- Model Size: 8 billion parameters
|
245 |
|
246 |
-
**Try Aya 23**
|
247 |
-
|
248 |
-
You can try out Aya 23 (35B) before downloading the weights in our hosted Hugging Face Space [here](https://huggingface.co/spaces/CohereForAI/aya-23).
|
249 |
-
|
250 |
### Usage
|
251 |
|
252 |
Please install transformers from the source repository that includes the necessary changes for this model
|
@@ -312,11 +313,13 @@ You can try Aya 23 in the Cohere [playground](https://dashboard.cohere.com/playg
|
|
312 |
|
313 |
### Citation info
|
314 |
```bibtex
|
315 |
-
@misc{
|
316 |
-
|
317 |
-
|
318 |
-
|
319 |
-
|
|
|
|
|
320 |
}
|
321 |
|
322 |
```
|
|
|
29 |
library_name: transformers
|
30 |
tags:
|
31 |
- GGUF
|
32 |
+
inference: false
|
33 |
quantized_by: andrijdavid
|
34 |
---
|
35 |
# aya-23-8B-GGUF
|
|
|
229 |
|
230 |
# Model Card for Aya-23-8B
|
231 |
|
232 |
+
**Try Aya 23**
|
233 |
+
|
234 |
+
You can try out Aya 23 (35B) before downloading the weights in our hosted Hugging Face Space [here](https://huggingface.co/spaces/CohereForAI/aya-23).
|
235 |
+
|
236 |
## Model Summary
|
237 |
|
238 |
Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. Aya 23 focuses on pairing a highly performant pre-trained [Command family](https://huggingface.co/CohereForAI/c4ai-command-r-plus) of models with the recently released [Aya Collection](https://huggingface.co/datasets/CohereForAI/aya_collection). The result is a powerful multilingual large language model serving 23 languages.
|
|
|
248 |
- Model: aya-23-8B
|
249 |
- Model Size: 8 billion parameters
|
250 |
|
|
|
|
|
|
|
|
|
251 |
### Usage
|
252 |
|
253 |
Please install transformers from the source repository that includes the necessary changes for this model
|
|
|
313 |
|
314 |
### Citation info
|
315 |
```bibtex
|
316 |
+
@misc{aryabumi2024aya,
|
317 |
+
title={Aya 23: Open Weight Releases to Further Multilingual Progress},
|
318 |
+
author={Viraat Aryabumi and John Dang and Dwarak Talupuru and Saurabh Dash and David Cairuz and Hangyu Lin and Bharat Venkitesh and Madeline Smith and Kelly Marchisio and Sebastian Ruder and Acyr Locatelli and Julia Kreutzer and Nick Frosst and Phil Blunsom and Marzieh Fadaee and Ahmet Üstün and Sara Hooker},
|
319 |
+
year={2024},
|
320 |
+
eprint={2405.15032},
|
321 |
+
archivePrefix={arXiv},
|
322 |
+
primaryClass={cs.CL}
|
323 |
}
|
324 |
|
325 |
```
|