Itay Levy

itlevy's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored a paper about 1 month ago

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Paper • 2411.19146 • Published Nov 28, 2024 • 14

updated a model 3 months ago

nvidia/Llama-3_1-Nemotron-51B-Instruct

Text Generation • Updated Oct 13, 2024 • 95.1k • 203

New activity in nvidia/Llama-3_1-Nemotron-51B-Instruct 3 months ago

Patching hf bug that creates wrong cache length if only inputs_embeds are passed to the model

#19 opened 3 months ago by

tomer-nv

DeciLMForCausalLM(DeciLMPreTrainedModel, GenerationMixin) for v4.50

#16 opened 3 months ago by

itlevy

add batch_size attribute to VariableCache

#15 opened 3 months ago by

itlevy

nvidia-open-model-license

#14 opened 3 months ago by

itlevy

nvidia-open-model-license

#13 opened 3 months ago by

itlevy

nvidia-open-model-license

#12 opened 3 months ago by

itlevy

v4.46 support

#7 opened 3 months ago by

itlevy

loading as llama model

1

#4 opened 4 months ago by

KnutJaegersberg

v4.45 support

#6 opened 3 months ago by

itlevy

updated a collection 3 months ago

Minitron

Collection

A family of compressed models obtained via pruning and knowledge distillation • 12 items • Updated 1 day ago • 60

New activity in nvidia/Llama-3_1-Nemotron-51B-Instruct 4 months ago

fixed flash_attention backward_compat

#3 opened 4 months ago by

itlevy

flash_attention_utils_backward_compat

#2 opened 4 months ago by

itlevy

liked a model 4 months ago

nvidia/Llama-3_1-Nemotron-51B-Instruct

Text Generation • Updated Oct 13, 2024 • 95.1k • 203