9 6 6

Nadav Timor

Nadav-Timor

AI & ML interests

None yet

Recent Activity

commented on an article 13 days ago

Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques

commented on their article 13 days ago

Universal Assisted Generation: Faster Decoding with Any Assistant Model

published an article 13 days ago

Speeding Up LLM Decoding with Advanced Universal Assisted Generation Techniques

View all activity

Organizations

Nadav-Timor's activity

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-7B 2 months ago

Vocab size in config.json mismatches the actual tokenizer size

#4 opened 2 months ago by

Fizzarolli

New activity in facebook/CyberSecEval 11 months ago

`llama3p-70b-rc3_vr_mid_3` & `llama3p-7b-rc3_vr_mid_2`?

#2 opened 11 months ago by

Nadav-Timor

New activity in AWS/MistralLite over 1 year ago

`max_position_embeddings=32768` and `precompute_freqs_cis` with `end=128_000`

#6 opened over 1 year ago by

Nadav-Timor

New activity in mistralai/Mistral-7B-Instruct-v0.1 over 1 year ago

`max_position_embeddings=32768` with "attention span of 131K tokens"

#57 opened over 1 year ago by

Nadav-Timor

New activity in joaogante/assisted_generation_demo over 1 year ago

Space isn't working because there is a runtime error

#1 opened over 1 year ago by

Nadav-Timor

New activity in Salesforce/codet5p-220m over 1 year ago

Challenges in reproducing the HumanEval scores reported in the paper with BigCode's Eval Harness

#2 opened almost 2 years ago by

Nadav-Timor

New activity in Salesforce/codegen-350M-mono almost 2 years ago

Padding?

#4 opened almost 2 years ago by

Nadav-Timor

New activity in gradio/sentence_builder about 2 years ago

Space isn't working because there is a runtime error

#3 opened about 2 years ago by

Nadav-Timor

New activity in stillerman/GLTR-token-probability-visualizer about 2 years ago

Update app.py

#1 opened about 2 years ago by

Nadav-Timor