Nadav Timor
Nadav-Timor
AI & ML interests
None yet
Recent Activity
commented on
an
article
about 1 month ago
Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques
commented on
their
article
about 1 month ago
Universal Assisted Generation: Faster Decoding with Any Assistant Model
published
an
article
about 1 month ago
Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques
Organizations
Nadav-Timor's activity
Vocab size in config.json mismatches the actual tokenizer size
5
#4 opened 3 months ago
by
Fizzarolli

`max_position_embeddings=32768` with "attention span of 131K tokens"
1
#57 opened over 1 year ago
by
Nadav-Timor

Space isn't working because there is a runtime error
3
#1 opened over 1 year ago
by
Nadav-Timor

Challenges in reproducing the HumanEval scores reported in the paper with BigCode's Eval Harness
6
#2 opened almost 2 years ago
by
Nadav-Timor

Padding?
#4 opened almost 2 years ago
by
Nadav-Timor
