Sam Havens
sam-mosaic
AI & ML interests
NLP
Recent Activity
authored
a paper
about 1 month ago
LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms
authored
a paper
about 1 month ago
MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining
Organizations
sam-mosaic's activity
How to submit models to the leaderboard?
3
#1 opened about 1 year ago
by
lewtun
fix padding side
#26 opened 10 months ago
by
iamroot
Data source
#3 opened 10 months ago
by
sam-mosaic
Fix add_generation_prompt in tokenizer.config
1
#8 opened 11 months ago
by
irenedea
Fix add_generation_prompt in tokenizer_config.json
1
#24 opened 11 months ago
by
irenedea
Add chat_template to tokenizer_config.json
1
#7 opened 11 months ago
by
irenedea
Add chat_template to tokenizer_config.json
1
#23 opened 11 months ago
by
irenedea
Add chat_template to tokenizer_config.json
2
#40 opened 12 months ago
by
irenedea
Data license
1
#2 opened 12 months ago
by
sam-mosaic
Memory allocation
1
#4 opened about 1 year ago
by
JDE65
License
1
#3 opened about 1 year ago
by
sam-mosaic
License CC-BY-4.0
#2 opened about 1 year ago
by
sam-mosaic
Data Cleaning
3
#1 opened over 1 year ago
by
Danivilanova
differenciate between Dolly and hhrlhf
1
#3 opened about 1 year ago
by
DRXD1000
Fix title in citation info
1
#35 opened about 1 year ago
by
ekurtic
License
3
#1 opened over 1 year ago
by
sam-mosaic
BOS and EOS tokens are the same?
1
#2 opened over 1 year ago
by
RonanMcGovern
How was fine-tuning done?
2
#34 opened over 1 year ago
by
RonanMcGovern
Add eos_token_id to generation config
#65 opened over 1 year ago
by
udhavsethi
HuggyLingo Bot: Add language information to your dataset
#2 opened over 1 year ago
by
librarian-bot