Sam Havens's picture

Sam Havens

sam-mosaic

·

sam_havens

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

View all activity

Organizations

sam-mosaic's activity

New activity in Nexusflow/Nexus_Function_Calling_Leaderboard 8 months ago

How to submit models to the leaderboard?

#1 opened about 1 year ago by

New activity in mosaicml/mpt-30b-chat 10 months ago

fix padding side

#26 opened 10 months ago by

New activity in jondurbin/truthy-dpo-v0.1 10 months ago

Data source

#3 opened 10 months ago by

New activity in mosaicml/mpt-7b-8k-chat 11 months ago

Fix add_generation_prompt in tokenizer.config

#8 opened 11 months ago by

New activity in mosaicml/mpt-30b-chat 11 months ago

Fix add_generation_prompt in tokenizer_config.json

#24 opened 11 months ago by

New activity in mosaicml/mpt-7b-8k-chat 11 months ago

Add chat_template to tokenizer_config.json

#7 opened 11 months ago by

New activity in mosaicml/mpt-30b-chat 11 months ago

Add chat_template to tokenizer_config.json

#23 opened 11 months ago by

New activity in mosaicml/mpt-7b-chat 12 months ago

Add chat_template to tokenizer_config.json

#40 opened 12 months ago by

New activity in tomasg25/scientific_lay_summarisation 12 months ago

Data license

#2 opened 12 months ago by

New activity in mosaicml/mpt-7b-8k about 1 year ago

Memory allocation

#4 opened about 1 year ago by

New activity in hackaprompt/hackaprompt-dataset about 1 year ago

License

#3 opened about 1 year ago by

New activity in KelvinJiang/freebase_qa about 1 year ago

License CC-BY-4.0

#2 opened about 1 year ago by

New activity in mosaicml/dolly_hhrlhf about 1 year ago

Data Cleaning

#1 opened over 1 year ago by

differenciate between Dolly and hhrlhf

#3 opened about 1 year ago by

New activity in mosaicml/mpt-7b-chat about 1 year ago

Fix title in citation info

#35 opened about 1 year ago by

New activity in codeparrot/self-instruct-starcoder over 1 year ago

License

#1 opened over 1 year ago by

New activity in mosaicml/mpt-7b-8k-chat over 1 year ago

BOS and EOS tokens are the same?

#2 opened over 1 year ago by

New activity in mosaicml/mpt-7b-chat over 1 year ago

How was fine-tuning done?

#34 opened over 1 year ago by

New activity in mosaicml/mpt-7b-instruct over 1 year ago

Add eos_token_id to generation config

#65 opened over 1 year ago by

New activity in sam-mosaic/vicuna_alpaca_hc3_chatml over 1 year ago

HuggyLingo Bot: Add language information to your dataset

#2 opened over 1 year ago by