BSC-LT/salamandraTA-2B-instruct-GGUF
Translation
•
2B
•
Updated
•
111
•
1
AI & ML interests
Machine Translation resources for a large variety of languages. Resources under this organization are unofficial and currently under development. Please be aware of usage limitations and additional information.
Recent Activity
View all activity
fdelucaf
updated
a
model
about 2 months ago
AudreyVM
updated
a
model
about 2 months ago
Post
1614
At the Language Technologies Unit of the Barcelona Supercomputing Center, we are developing State of the Art Large Language and Voice Models through various national and international projects. It is an exciting time to be working in generative AI!
We are looking for bright and motivated individuals to help us achieve ambitious goals. Our latest opening for the Innovation group that develops powerful and socially useful applications for AI technology might be for you. Check it out here:
https://www.bsc.es/join-us/job-opportunities/3025lsltre2
We are looking for bright and motivated individuals to help us achieve ambitious goals. Our latest opening for the Innovation group that develops powerful and socially useful applications for AI technology might be for you. Check it out here:
https://www.bsc.es/join-us/job-opportunities/3025lsltre2
carlosep93
authored
a
paper
about 1 year ago
Post
2433
Multilingual RAG optimized models and datasets available from the Language Technologies Unit @ the Barcelona Supercomputing Unit
We are releasing new RAG-optimized multilingual models and dataset, within the AINA project contributions:
projecte-aina/FlorRAG , based on out Bloom Flor6.3b model, capable of RAG in Catalan, Spanish and English
projecte-aina/RAG_Multilingual , a 56K+ instructional dataset with human-like answers created from kernel-of-truth of extractive datasets using a Mixtral8x7b model
We are releasing new RAG-optimized multilingual models and dataset, within the AINA project contributions:
projecte-aina/FlorRAG , based on out Bloom Flor6.3b model, capable of RAG in Catalan, Spanish and English
projecte-aina/RAG_Multilingual , a 56K+ instructional dataset with human-like answers created from kernel-of-truth of extractive datasets using a Mixtral8x7b model