Hugging Face's logo
Margaux Ammour's picture
16 1 26

Margaux Ammour

mammour
·

AI & ML interests

Instead of looking for something that is potentially harmful, better grasp what we can already make happen Artificially Augmented Intelligence advocate

Recent Activity

liked a model 7 days ago
deepcogito/cogito-v1-preview-qwen-32B
reacted to sr-rai's post with 🤗 8 days ago
ExLlamaV3 is out. And it introduces EXL3 - a new SOTA quantization format! "The conversion process is designed to be simple and efficient and requires only an input model (in HF format) and a target bitrate. By computing Hessians on the fly and thanks to a fused Viterbi kernel, the quantizer can convert a model in a single step, taking a couple of minutes for smaller models, up to a few hours for larger ones (70B+) (on a single RTX 4090 or equivalent GPU.)" Repo: https://github.com/turboderp-org/exllamav3
upvoted a paper 9 days ago
Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness
View all activity

Organizations

Ammour family's profile picture

mammour's activity

New activity in mistralai/Mistral-Small-24B-Instruct-2501 2 months ago

Mistral Small 24 B

4
#19 opened 2 months ago by
HandsomeMagyar

Why increase censorship?

21
#20 opened 2 months ago by
notafraud
New activity in Qwen/QwQ-32B-Preview 5 months ago

multi GPU inferencing

2
#18 opened 5 months ago by
cjj2003
New activity in Jacoby746/Casual-Magnum-34B-exl2-4.0bpw 6 months ago

Error during inference

7
#1 opened 6 months ago by
Jellon
New activity in mistralai/Mistral-Small-Instruct-2409 7 months ago

Please consider changing the instruct format!

15
19
#10 opened 7 months ago by
MarinaraSpaghetti
New activity in nvidia/Llama3-ChatQA-1.5-8B 12 months ago

What is the context length?

3
#2 opened 12 months ago by
softwareweaver
New activity in bartowski/airoboros-2.2.1-y34b-exl2 over 1 year ago

Changes compared to previous quantization ?

2
#1 opened over 1 year ago by
mammour
New activity in migtissera/HelixNet over 1 year ago

A tiny request for v2

1
2
#6 opened over 1 year ago by
mammour
New activity in TheBloke/Mistral-7B-OpenOrca-AWQ over 1 year ago

Stuck in loading

1
#1 opened over 1 year ago by
Nicoolodion
New activity in Undi95/MistRP-AirOrca-7B over 1 year ago

Context length?

2
#1 opened over 1 year ago by
Delcos
New activity in TheBloke/13B-Chimera-GGML almost 2 years ago

Hey You *na'vi sounds*

3
#1 opened almost 2 years ago by
mammour
New activity in prompthero/openjourney-v4 over 2 years ago

Could you upload the 4GB variants of the models?

1
#4 opened over 2 years ago by
ProGamerGov