On Coding Your First Attention
•
7
Jaward Sesay
Jaward
AI & ML interests
I like to train large deep neural nets too 🧠🤖💥 | First Paper (AutoAgents: A Framework for Automatic Agent Generation) Accepted @ IJCAI 2024 | Role Model Karpathy
Articles
Organizations
Posts
26
Post
30
Build your own GPT-4 Tokenizer! -
@karpathy
's minbpe exercise.
Step 2: RegexTokenizer
Leading karpathy's regex.py by .27s :)
GPT4 Tokenizer builds on regex split patterns, so just a few more lines of code to get there (Step 3 coming soon)
Step 2: RegexTokenizer
Leading karpathy's regex.py by .27s :)
GPT4 Tokenizer builds on regex split patterns, so just a few more lines of code to get there (Step 3 coming soon)
Post
563
When untrained tokens play "catch me if you can" the Fishing For Margikarp paper is the detective:)
The playbook:
- Inspect token vocab & study encode/decode pattern.
- Brute-force on architecture-dependent indicators (same matrix in token embeddings and final layer) to identify untrained tokens.
- Then verify if identified tokens are out of distribution by prompting a target llm (with no tied threshold).
Quite a bait huh, Cohere:)
The playbook:
- Inspect token vocab & study encode/decode pattern.
- Brute-force on architecture-dependent indicators (same matrix in token embeddings and final layer) to identify untrained tokens.
- Then verify if identified tokens are out of distribution by prompting a target llm (with no tied threshold).
Quite a bait huh, Cohere:)
Papers
1
models
2
datasets
None public yet