James Barry

Research Scientist @ IBM Research | PhD from ADAPT Centre, Dublin City University

[James Barry @jamesarbarry]

If any Irish speakers are interested in helping annotate some of the BLEnD examples to Irish, please let me know (can be as little as a few examples). We aim to have Irish included in the next release.

https://t.co/my3WDYgaCR

[James Barry @jamesarbarry]

@NotTheBudha @MSripadarao @StasBekman @JordanNanos @OpenAI @AnthropicAI @xai Handy thing about slurm is you can just activate a venv and quickly launch your script, most IDEs have good support for remote dev.
With k8s you need to build your image, host it on a registry, mount a volume etc. Can be a bit harder to debug things/fix env issues as they arise.

[James Barry @jamesarbarry]

@mark_l_watson Totally get the sentiment but sometimes it's good to be able to see the main functionality without the layers of abstraction of large libraries. I think the first example of tool calling agents I'd seen in vanilla python code was this helpful reference: https://t.co/rFmcGolD9x

[James Barry @jamesarbarry]

@_philschmid @huggingface Been following your guides this year for distributed training, instruction tuning, model serving, they've all been so relevant and helpful. Keep it up!

[James Barry @jamesarbarry]

IBM Research Europe (UK) are looking for interns in generative AI in sustainability: reasoning over multimodal data, foundations models in the climate/materials domain, and exploring agentic systems. Please consider applying here: https://t.co/2VILZDa4KC

[James Barry @jamesarbarry]

@carrigmat Ah I see, yes the v0.3 Mistral Instruct model has new special tokens like [TOOL_CALL], [TOOL_RESULT] and their closing equivalents, so I can see how they would be interleaved in the chat, thanks!

[James Barry @jamesarbarry]

@carrigmat When we have a "role": "tool" message, does this get aliased as a "user" or "assistant" message in the chat history, or are the chat templates modified to handle these cases?

[James Barry @jamesarbarry]

Details of the paper can be found here: https://t.co/HAIJweYI86

[James Barry @jamesarbarry]

Had a great time presenting our Demo Paper, KnowledgeHub: An End-to-End Tool for Assisted Scientific Discovery at IJCAI 2024 in Jeju Island, Korea today!

[James Barry @jamesarbarry]

@liliang_ren Congrats Liliang, very exciting work!

[James Barry @jamesarbarry]

@francoisfleuret Reminds me of Norvig’s PAIP that mentions a student used to write 1 letter names so his variables would be looked up faster, but “Every variable, regardless of its name, is just a memory location, and the time to access the location does not depend on the name of the variable.”

[James Barry @jamesarbarry]

With #Nvidia stock rallying, competitors are no doubt trying to capture back some of that market share.
Realistically how big are Nvidia's hardware/software moats - how likely is wider spread adoption of:

- AMD/ROCm
- Intel/Habana
- Apple/MLX
- Tesla/Dojo?

[James Barry @jamesarbarry]

@jackminong @StasBekman True. Another problem I find with remote editing is that there can be latency when opening and saving files etc. (esp. if someone's running some heavy program on the remote), and if you're using emacs or vim where keystrokes feel automatic, the latency messes up the flow

[James Barry @jamesarbarry]

@StasBekman @jackminong Developing on a remote cluster is never as seamless as local. VSCode remote extension can be quite finicky, with random disconnects and having to open your project again on a login and then compute node. Alternatives such as Emacs in Tramp mode aren't painless either

[James Barry @jamesarbarry]

@sarahookr Catalan BERT has a section: 6.3 Data contamination which takes a look at this (https://t.co/DP5rL62LWb)

cc @OnadeGibert

[James Barry @jamesarbarry]

@srush_nlp His (with Mark Johnson) chapter on parsing is brilliant: https://t.co/5Fa2mbhyjQ

I can't seem to find the complete collection of chapters, best I could find was a draft from 2013: https://t.co/I2Xebjvxto

I hope that these notes will be collected and preserved somewhere

[James Barry @jamesarbarry]

Circulating to anyone interested in working with Celtic Languages!

[Matthew Carrigan @carrigmat]

The Irish language section might be of interest to either @jamesarbarry or @emmacarrigan! (I am not nearly confident enough in my fluency to try)

[James Barry @jamesarbarry]

If anyone is interested in learning about the Common Lisp Object System (classes and object-oriented programing in #Lisp), I wrote a blog post about it here, using the example of scoring a game of bowling:

https://t.co/9wGWDzV7jg

[James Barry @jamesarbarry]

@MOMeachair For me I was mainly exposed to NLP from the deep learning side, so I always wanted to learn more about previous approaches. And you're right, there's too many things on the list and too little time 😅

[James Barry @jamesarbarry]

I'm going through Michael Collins' 2013 Columbia NLP course that was on Coursera. Here is an implementation of a trigram UD POS tagger using the Viterbi Algorithm as described in the Chapter 2 notes: https://t.co/gM5JKBUsAo

[James Barry @jamesarbarry]

@MOMeachair Thanks Mícheál! I took a brief look at this course in 2016 but am only really going through it properly now. It's a real gem, and it's nice to look at some of the older stuff too!