Hugging Face's logo

YeMoKoo
/
LLM-continual-learning

Safetensors
Model card Files
xet
 Community
YeMoKoo commited on
Commit
982916d
·
verified ·
1 Parent(s): 9564235

Add final checkpoint: g2_ffn_attn_1phase_conversation_loadfix_v3

Browse files
Files changed (13) hide show
  1. .gitattributes +9 -0
  2. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/.metadata +3 -0
  3. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__0_0.distcp +3 -0
  4. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__0_1.distcp +3 -0
  5. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__1_0.distcp +3 -0
  6. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__1_1.distcp +3 -0
  7. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__2_0.distcp +3 -0
  8. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__2_1.distcp +3 -0
  9. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__3_0.distcp +3 -0
  10. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__3_1.distcp +3 -0
  11. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/common.pt +3 -0
  12. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/metadata.json +1 -0
  13. g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/latest_checkpointed_iteration.txt +1 -0
.gitattributes CHANGED
@@ -85,3 +85,12 @@ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/
85
  g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
86
  g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
87
  g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
85
  g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
86
  g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
87
  g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/kd_init/iter_0000600/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
88
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/.metadata filter=lfs diff=lfs merge=lfs -text
89
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
90
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
91
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
92
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
93
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
94
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
95
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
96
+ g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96b66a4835e21e6d8ca1c4ebaea6e703b8bb6fa9ad6e73449bc6ecdaacbcbef
3
+ size 315164
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41b1e29473970a24e9015072f874bd5ee065ba9b75d5775d1c903b6753536b3
3
+ size 167052408
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__0_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05c23babf55596483dd4ae9bdc7b66b0a8d16c271e21942c1a41654be7dc479
3
+ size 167086772
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c22ef026f0d009d1a49f5855d739cf48b37333f0912825349e6f4922d85f36
3
+ size 166878800
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__1_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4807a1ecba1a594a63b6636b5461fd27bc36484c8db41fef5e49f3dd86edd7
3
+ size 166876264
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5755460e84a5fd5d8f87b9e979b4ca03925c13cc4d578b5b054589c8f6cbabac
3
+ size 166685732
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__2_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e80be7b9eabb682703becf6058775044741f880a03b224bab14105b7b9cd35
3
+ size 167343452
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37243b078d3e8c59902758a23f328f568722c56d53834b0386128e551a2f1f5
3
+ size 166685732
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/__3_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7823e254ff83f36ba1d4aced4b69313002051b97ca2bbd2de91630a599988b19
3
+ size 167343452
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/common.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da350657c5439b9ed7c221d841cd89e287042cf84e1e398fcfd9f4c59319b483
3
+ size 30108
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/iter_0001800/metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}
g2_wiki_code_conversation/kd_1phase/ffn_attn_shared_router/conversation/one_phase/latest_checkpointed_iteration.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 1800