s1ghhh/Llama-2-13b-Drop8Block
Updated
•
5
•
2
LLM-Drop
Model weights of paper "What Matters in Transformers? Not All Attention is Needed" (https://arxiv.org/abs/2406.15786)
-
-
s1ghhh/Llama-2-13b-Drop4Block
Updated • 3 • 2 -
s1ghhh/Llama-2-13b-Drop4Attn
Updated • 6 • 2 -
s1ghhh/Llama-2-13b-Drop8Attn
Updated • 68 • 2 -
s1ghhh/Llama-2-13b-Drop4MLP
Updated • 7 • 2 -
s1ghhh/Llama-2-13b-Drop8MLP
Updated • 4 • 2 -
s1ghhh/Mistral-7B-v0.1-Drop4Block
Updated • 3 • 2 -
s1ghhh/Mistral-7B-v0.1-Drop8Block
Updated • 3 • 2 -
s1ghhh/Mistral-7B-v0.1-Drop4Attn
Updated • 8 • 2 -
s1ghhh/Mistral-7B-v0.1-Drop8Attn
Updated • 6 • 2 -
s1ghhh/Mistral-7B-v0.1-Drop4MLP
Updated • 8 • 2 -
s1ghhh/Mistral-7B-v0.1-Drop8MLP
Updated • 2 • 2 -
s1ghhh/Llama-2-70b-Drop
Text Generation • Updated • 41 • 2 -
s1ghhh/Llama-3-70b-Drop
Text Generation • Updated • 88 • 3