William J.B. Mattingly
@wjbmattingly.bsky.social
Digital Nomad · Historian · Data Scientist · NLP · Machine Learning
Cultural Heritage Data Scientist at Yale
Former Postdoc in the Smithsonian
Maintainer of Python Tutorials for Digital Humanities
https://linktr.ee/wjbmattingly
Cultural Heritage Data Scientist at Yale
Former Postdoc in the Smithsonian
Maintainer of Python Tutorials for Digital Humanities
https://linktr.ee/wjbmattingly
2B model: huggingface.co/small-models...
October 24, 2025 at 2:59 PM
2B model: huggingface.co/small-models...
4B model: huggingface.co/small-models...
October 24, 2025 at 2:59 PM
4B model: huggingface.co/small-models...
8B model: huggingface.co/small-models...
October 24, 2025 at 2:59 PM
8B model: huggingface.co/small-models...
Ahh no worries!! Thanks! I hope you had a nice vacation
August 25, 2025 at 2:55 PM
Ahh no worries!! Thanks! I hope you had a nice vacation
No problem! It's hard to fit a good answer in 300 characters =) Feel free to DM me any time.
August 13, 2025 at 8:02 PM
No problem! It's hard to fit a good answer in 300 characters =) Feel free to DM me any time.
Also, if you are doing a full finetune vs LoRa adapters is another thing to consider. Also, depends on the model arch.
August 13, 2025 at 8:00 PM
Also, if you are doing a full finetune vs LoRa adapters is another thing to consider. Also, depends on the model arch.
I hate saying this, but it's true: it depends. For line-level medieval Latin (out of scope, but small problem size), 1-3k examples seems to be fine. For page level out of scope problems, it really becomes more challenging and very model dependent, 1-10k in my experience.
August 13, 2025 at 7:59 PM
I hate saying this, but it's true: it depends. For line-level medieval Latin (out of scope, but small problem size), 1-3k examples seems to be fine. For page level out of scope problems, it really becomes more challenging and very model dependent, 1-10k in my experience.
Congrats on the new job!!
August 13, 2025 at 3:13 PM
Congrats on the new job!!