Hugging Face's logo
Ilyas Moutawwakil's picture
31 5 50

Ilyas Moutawwakil

IlyasMoutawwakil
lysandre's profile picture Weyaxi's profile picture echarlaix's profile picture
·
IlyasMoutawwakil

AI & ML interests

Optimization, LLMs, Hardware, Backends, ..

Articles

Organizations

Hugging Face's profile picture Training Transformers Together's profile picture HugGAN Community's profile picture ONNXConfig for all's profile picture Hugging Face Optimum's profile picture HuggingFaceM4's profile picture Hugging Face H4's profile picture Optimum AMD's profile picture Social Post Explorers's profile picture That Time I got Reincarnated to a LowRes Hugging Face Organization's profile picture AI Energy Star Project's profile picture Optimum-Benchmark's profile picture Optimum-Intel's profile picture

IlyasMoutawwakil's activity

New activity in IlyasMoutawwakil/tiny-random-LlavaForConditionalGeneration about 2 months ago

Does not contain `<image>` token.

1
#1 opened about 2 months ago by Xenova
New activity in optimum/llm-perf-leaderboard about 2 months ago

How to request performance evaluation with 'llm-perf-backend'?

3
#27 opened 2 months ago by LLMNewbie
New activity in optimum/llm-perf-leaderboard 4 months ago

How often do you update the leaderboard?

2
#22 opened 6 months ago by zhiminy

Cache the Results?

2
#16 opened 7 months ago by dark-pen

What are differences between Max Allocated Memory, Max Reserved Memory and Max Used Memory?

1
#21 opened 6 months ago by zhiminy

How to download the table as csv file?

5
#18 opened 6 months ago by zhiminy

Where to download the leaderboard?

2
#26 opened 5 months ago by zhiminy

What is the testing prompt?

1
#23 opened 6 months ago by zhiminy

🚩 Report: Not working

1
#24 opened 5 months ago by gblazex

I have added an application to Open LLM Leaderboard and see my scores on it, but how do I use the LLM Performance Leaderboard?

1
#25 opened 5 months ago by yyjjtt
New activity in optimum/llm-perf-leaderboard 5 months ago

Mention models with latencies that are too high
#6 opened 11 months ago by tomaarsen

Bug report , application fail to start

2
#15 opened 7 months ago by cormak
New activity in optimum/llm-perf-leaderboard 6 months ago

Accuracy differences for models with quantization

10
#12 opened 10 months ago by kmcgrath

Why do we need this attribute at all?

3
#20 opened 6 months ago by zhiminy

Control panel does not work now

3
#19 opened 6 months ago by zhiminy
New activity in optimum/all-MiniLM-L6-v2 8 months ago

Is this ONNX?

8
#1 opened 8 months ago by drmeir
New activity in IlyasMoutawwakil/llm-bar-race 8 months ago

Fix tab name typo

1
#1 opened 8 months ago by gabrielmbmb
New activity in optimum/llm-perf-leaderboard 9 months ago

Is there any example for each LLM performance evaluation?

2
#14 opened 9 months ago by Ssicayoon

cerebras BTLM models
#11 opened 10 months ago by mrseeker87

Requesting for StableBeluga-13B

2
#13 opened 10 months ago by aliencaocao

Llama-2

1
#10 opened 10 months ago by GHW
New activity in optimum/llm-perf-leaderboard 10 months ago

Fix typo

1
#9 opened 10 months ago by regisss

Parameters sorting does not work properly
#7 opened 10 months ago by osanseviero

Score and Latency are mixed up in A100 80GB plot

2
#8 opened 10 months ago by jelmers

Hardware request : 2*48GB NVIDIA RTX A6000

1
#3 opened 11 months ago by adnan-ahmad-tub

Why are the float32 versions a few tokens per second faster than their float16 versions?

2
#1 opened 11 months ago by vcoyk

What is Average H4 Score?

1
#2 opened 11 months ago by adnan-ahmad-tub

Rename "Submit" to "Filter"

2
#4 opened 11 months ago by tomaarsen

Make plot responsive to control panel

3
#5 opened 11 months ago by tomaarsen
New activity in HuggingFaceH4/open_llm_leaderboard 11 months ago

Add a speed column (token/s)

1
#96 opened 11 months ago by louis030195
New activity in tiiuae/falcon-40b 12 months ago

corrected a typo
#5 opened 12 months ago by IlyasMoutawwakil