Chenyang Song

Raincleared's activity

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

commented a paper about 1 month ago

BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity

Paper • 2507.08771 • Published Jul 11 • 9 •

1

New activity in SparseLLM/prosparse-llama-2-7b 8 months ago

Model not running on CPU, due to flash_attn package requirement.

4

#8 opened 8 months ago by

Akash1003

New activity in SparseLLM/ReluLLaMA-7B 8 months ago

Adding `safetensors` variant of this model

#3 opened 8 months ago by

SFconvertbot

New activity in SparseLLM/sparsing-law-0.1b-relu 8 months ago

Adding `safetensors` variant of this model

#1 opened 8 months ago by

SFconvertbot

New activity in openbmb/MiniCPM-S-1B-sft 10 months ago

Adding `safetensors` variant of this model

#1 opened 10 months ago by

SFconvertbot

commented a paper 10 months ago

Sparsing Law: Towards Large Language Models with Greater Activation Sparsity

Paper • 2411.02335 • Published Nov 4, 2024 • 11 •

1

New activity in SparseLLM/prosparse-llama-2-7b 10 months ago

why does this model use FP32??

1

#6 opened 10 months ago by

purejomo

New activity in SparseLLM/prosparse-llama-2-7b over 1 year ago

Evaluation using UltraEval

4

#3 opened over 1 year ago by

hustzxd

Clarification on Output Neuron Pruning Method in "Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time"

5

#2 opened over 1 year ago by

adamgallas

New activity in SparseLLM/prosparse-llama-2-7b-predictor over 1 year ago

Clarification on Output Neuron Pruning Method in "Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time"

2

#1 opened over 1 year ago by

adamgallas

New activity in SparseLLM/prosparse-llama-2-7b over 1 year ago

Training Code

2

#1 opened over 1 year ago by

Gatozu35

New activity in PowerInfer/prosparse-llama-2-7b-gguf over 1 year ago

How ti train sparse model like those

5

#1 opened over 1 year ago by

mobinx

How ti train sparse model like those

5

#1 opened over 1 year ago by

mobinx

How ti train sparse model like those

5

#1 opened over 1 year ago by

mobinx