Hugging Face's logo
Feliks Zaslavskiy's picture
23 4

Feliks Zaslavskiy

felixz
gar1t's profile picture PeepDaSlan9's profile picture
·

AI & ML interests

NLP

Organizations

DataScienceGuild's profile picture RealTimeLiveAIForHealth's profile picture

felixz's activity

New activity in open-llm-leaderboard/open_llm_leaderboard 6 months ago

Bug- model show incorrect # Params

4
#499 opened 6 months ago by felixz
New activity in felixz/open_llm_leaderboard 7 months ago

The code does not work...

4
#1 opened 7 months ago by zhiminy
New activity in open-llm-leaderboard/open_llm_leaderboard 9 months ago

Gradio ApI stopped working.

7
#273 opened 10 months ago by felixz
New activity in open-llm-leaderboard/open_llm_leaderboard 10 months ago

About New Rate Limit System

4
#272 opened 10 months ago by mhemetfaik

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

4
#266 opened 10 months ago by felixz

Model parameter numbers are incorrect

8
#253 opened 10 months ago by ekurtulus

Unable to Query the Leaderboard via Gradio Client.

10
#248 opened 10 months ago by felixz

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

15
#207 opened 11 months ago by jaspercatapang
New activity in open-llm-leaderboard/open_llm_leaderboard 11 months ago

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

6
#202 opened 11 months ago by TNTOutburst

Same model appear multiple times on leaderboard with different scores

6
#180 opened 11 months ago by felixz

The 16Bit evaluation of WizardLM/WizardLM-70B is missing from results

1
#200 opened 11 months ago by felixz

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

2
#181 opened 11 months ago by felixz

None of the UL2 based models have been evaluated.

5
#114 opened 12 months ago by felixz

Idea about model details

4
#187 opened 11 months ago by flozi00

Did you change the way you run evals today?

8
#178 opened 11 months ago by bleysg

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

3
#160 opened 11 months ago by clefourrier

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

2
#163 opened 11 months ago by spaceman7777

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

5
#164 opened 11 months ago by vonjack

What exactly is difference between "finetuned" and "instruction-tuned"?

1
#167 opened 11 months ago by felixz
New activity in lmsys/chatbot-arena-leaderboard 11 months ago

Please expose API endpoint

1
#3 opened 11 months ago by felixz
New activity in open-llm-leaderboard/open_llm_leaderboard 11 months ago

Benchmarks for GPT-3.5 & GPT-4 for comparison

10
#145 opened 11 months ago by mantrakp
New activity in open-llm-leaderboard/open_llm_leaderboard 12 months ago

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

4
#110 opened 12 months ago by felixz
New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

Progress is too slow

1
#16 opened about 1 year ago by felixz