Mychatui
🚀
testing chatui
Luis Vasquez
LuisVasquezBSC
AI & ML interests
NLP @ BSC
Recent Activity
updated
a Space
about 15 hours ago
langtech-annotators/redteam
liked
a dataset
30 days ago
langtech-languagemodeling/veritasQA
liked
a Space
3 months ago
CohereLabsCommunity/m-rewardbench
Organizations
LuisVasquezBSC's activity
updated
a
Space
about 15 hours ago
liked
a
dataset
30 days ago
liked
a
Space
3 months ago
liked
a
dataset
5 months ago
Tutorial: Use Llama-Guard-3-8B as a classifier AND get safety categories
1
#21 opened 6 months ago
by
LuisVasquezBSC
updated
4
datasets
7 months ago
Upload folder using huggingface_hub
#1 opened 7 months ago
by
LuisVasquezBSC
Upload folder using huggingface_hub
#4 opened 7 months ago
by
LuisVasquezBSC
Upload folder using huggingface_hub
#5 opened 7 months ago
by
LuisVasquezBSC
Upload folder using huggingface_hub
#6 opened 7 months ago
by
LuisVasquezBSC
reacted to
Tonic's
post with 👀
7 months ago
Post
1873
🙋🏻♂️ Hey there folks ,
🦎Salamandra release by @mvillegas and team
@BSC_CNS
BSC-LT
is absolutely impressive so far !
perhaps the largest single training dataset of high quality text to date of 7.8 trillion tokens in 35 European languages and code.
the best part : the data was correctly licenced so it's actually future-proof!
the completions model is really creative and instruct fine tuned version is very good also.
now you can use such models for multi-lingual enterprise applications with further finetunes , long response generation, structured outputs (coding) also works.
check out 👇🏻
the collection : BSC-LT/salamandra-66fc171485944df79469043a
the repo : https://github.com/langtech-bsc/salamandra
7B-Instruct demo : Tonic/Salamandra-7B
🦎Salamandra release by @mvillegas and team
@BSC_CNS
BSC-LT
is absolutely impressive so far !perhaps the largest single training dataset of high quality text to date of 7.8 trillion tokens in 35 European languages and code.
the best part : the data was correctly licenced so it's actually future-proof!
the completions model is really creative and instruct fine tuned version is very good also.
now you can use such models for multi-lingual enterprise applications with further finetunes , long response generation, structured outputs (coding) also works.
check out 👇🏻
the collection : BSC-LT/salamandra-66fc171485944df79469043a
the repo : https://github.com/langtech-bsc/salamandra
7B-Instruct demo : Tonic/Salamandra-7B
liked
a
Space
8 months ago
liked
a
Space
10 months ago