Feliks Zaslavskiy's picture

23 4

Feliks Zaslavskiy

felixz

·

AI & ML interests

NLP

Organizations

felixz's activity

New activity in felixz/open_llm_leaderboard over 1 year ago

The code does not work...

#1 opened over 1 year ago by

New activity in open-llm-leaderboard/open_llm_leaderboard over 1 year ago

Gradio ApI stopped working.

#273 opened over 1 year ago by

About New Rate Limit System

#272 opened over 1 year ago by deleted

New activity in open-llm-leaderboard/open_llm_leaderboard almost 2 years ago

WizardLM 30B model seems to rank way lower then it probably should be at.

#266 opened almost 2 years ago by

Model parameter numbers are incorrect

#253 opened almost 2 years ago by

Unable to Query the Leaderboard via Gradio Client.

#248 opened almost 2 years ago by

[FLAG] deepnight-research/llama-2-70B-inst: Identical models on leaderboard

#207 opened almost 2 years ago by

[FLAG] Voicelab/trurl-2-13b: training data surely includes the test data, right?

#202 opened almost 2 years ago by

Same model appear multiple times on leaderboard with different scores

#180 opened almost 2 years ago by

WizzardLM70B request failed. I think many ppl are anticipating results for this one.

#181 opened almost 2 years ago by

None of the UL2 based models have been evaluated.

#114 opened almost 2 years ago by

Idea about model details

#187 opened almost 2 years ago by

Did you change the way you run evals today?

#178 opened almost 2 years ago by

[Help needed] Re-labelling models to separate different kinds of fine-tuning

#160 opened almost 2 years ago by

Can paying for the compute to get a model posted be opened up to more parties than Meta, please?

#163 opened almost 2 years ago by

Please add Qwen-7b and Qwen-7b-chat to the LLM leaderboard.

#164 opened almost 2 years ago by

Benchmarks for GPT-3.5 & GPT-4 for comparison

#145 opened almost 2 years ago by

Some models have missing "Param# (B)".

#110 opened almost 2 years ago by