InternLM / InternLM/InternLM-XComposer

About PLora

Open
#313 0 comments 0 reactions 1 assignee Claimed by @yhcao6 View on GitHub
Dominant language
Python
Stars
2.9k
Forks
175
PR merge metrics
No merged PRs in 30d

Description

If I want to turn off parameters in the Plora section during training, which layers of the model do I need to turn off parameter iterations?
"model.layers.0.attention.wo.Plora_A.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.attention.wo.Plora_B.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.attention.wo.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.attention.wqkv.Plora_A.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.attention.wqkv.Plora_B.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.attention.wqkv.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.attention_norm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w1.Plora_A.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w1.Plora_B.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w1.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w2.Plora_A.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w2.Plora_B.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w2.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w3.Plora_A.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w3.Plora_B.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.feed_forward.w3.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.ffn_norm.weight": "pytorch_model-00001-of-00002.bin",

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.