Itay Levy

itlevy's activity

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

New activity in nvidia/Llama-3_1-Nemotron-51B-Instruct about 1 month ago

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

#19 opened about 1 month ago by tomer-nv

New activity in nvidia/Llama-3_1-Nemotron-51B-Instruct about 2 months ago

DeciLMForCausalLM(DeciLMPreTrainedModel, GenerationMixin) for v4.50

#16 opened about 2 months ago by itlevy

add batch_size attribute to VariableCache

#15 opened about 2 months ago by itlevy

nvidia-open-model-license

#14 opened about 2 months ago by itlevy

nvidia-open-model-license

#13 opened about 2 months ago by itlevy

nvidia-open-model-license

#12 opened about 2 months ago by itlevy

v4.46 support

#7 opened about 2 months ago by itlevy

loading as llama model

1

#4 opened about 2 months ago by KnutJaegersberg

v4.45 support

#6 opened about 2 months ago by itlevy

fixed flash_attention backward_compat

#3 opened about 2 months ago by itlevy

flash_attention_utils_backward_compat

#2 opened about 2 months ago by itlevy

flash_attention_utils_backward_compat

#2 opened about 2 months ago by itlevy