Hugging Face's logo

multi-token
/
shiftedattn-9-21-qwen25coder-instr-from-scratch-n64w8-lr1-e6

Model card Files
xet
Community
Snyhlxde commited on
Commit
d4fafc4
·
1 Parent(s): e7c534a

upload model

Browse files
Files changed (27) hide show
  1. .gitattributes +18 -0
  2. added_tokens.json +3 -0
  3. chat_template.jinja +3 -0
  4. config.json +3 -0
  5. generation_config.json +3 -0
  6. global_step43000/.gitattributes +8 -0
  7. global_step43000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  8. global_step43000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  9. global_step43000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  10. global_step43000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  11. global_step43000/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  12. global_step43000/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  13. global_step43000/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  14. global_step43000/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  15. latest +3 -0
  16. merges.txt +3 -0
  17. rng_state_0.pth +3 -0
  18. rng_state_1.pth +3 -0
  19. rng_state_2.pth +3 -0
  20. rng_state_3.pth +3 -0
  21. scheduler.pt +3 -0
  22. special_tokens_map.json +3 -0
  23. tokenizer_config.json +3 -0
  24. trainer_state.json +3 -0
  25. training_args.bin +3 -0
  26. vocab.json +3 -0
  27. zero_to_fp32.py +3 -0
.gitattributes CHANGED
@@ -33,3 +33,21 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ chat_template.jinja filter=lfs diff=lfs merge=lfs -text
37
+ merges.txt filter=lfs diff=lfs merge=lfs -text
38
+ rng_state_1.pth filter=lfs diff=lfs merge=lfs -text
39
+ scheduler.pt filter=lfs diff=lfs merge=lfs -text
40
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
41
+ zero_to_fp32.py filter=lfs diff=lfs merge=lfs -text
42
+ config.json filter=lfs diff=lfs merge=lfs -text
43
+ generation_config.json filter=lfs diff=lfs merge=lfs -text
44
+ global_step43000 filter=lfs diff=lfs merge=lfs -text
45
+ latest filter=lfs diff=lfs merge=lfs -text
46
+ special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
47
+ trainer_state.json filter=lfs diff=lfs merge=lfs -text
48
+ rng_state_3.pth filter=lfs diff=lfs merge=lfs -text
49
+ added_tokens.json filter=lfs diff=lfs merge=lfs -text
50
+ rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
51
+ rng_state_2.pth filter=lfs diff=lfs merge=lfs -text
52
+ tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
53
+ vocab.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
3
+ size 605
chat_template.jinja ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f
3
+ size 2507
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebeb2c8c5b579645b34f43a9192d77e869763cc4a71f16515a0d6661b6a6fc6e
3
+ size 1325
generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69dbae630519cf998049cce7936711f8a33ae1cc0f0859c81a1e8ad0eec58fcc
3
+ size 242
global_step43000/.gitattributes ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ zero_pp_rank_1_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
2
+ zero_pp_rank_2_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
3
+ zero_pp_rank_3_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
4
+ bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
5
+ bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
6
+ bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
7
+ bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt filter=lfs diff=lfs merge=lfs -text
8
+ zero_pp_rank_0_mp_rank_00_model_states.pt filter=lfs diff=lfs merge=lfs -text
global_step43000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526142eb9aca99cd02ee05f9ff4fe51e3934b595950419598a01bd5962a437ee
3
+ size 22846856147
global_step43000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646e50986613ea6a61b8003f1eea3996a16fc49c34b83f502538dda4f6159903
3
+ size 22846856147
global_step43000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9e45562c723468952086841b9001effd0e5b7d47bb6f2aa5435286112167b0
3
+ size 22846856147
global_step43000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1712e184679ae2d0fb5a54436edfe62132bb56237a282ba9b974c0425ea7f53c
3
+ size 22846856147
global_step43000/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9871bf82a634406249ff0b42da97fac3d94d4854b3cc272bed32f471f6188379
3
+ size 174112
global_step43000/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02c86fa5621e8e3c4eea9fef3fec26cde677eac082b32b2910c34c255bbe891
3
+ size 174112
global_step43000/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49df454ec8c9f5e0dad401ee552b28af623e98f33ce4196c6ff50bf14eb1b4b0
3
+ size 174112
global_step43000/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b94330b735d0c9cbcfa1ae9158282966a05827a4dc99b9711e6e3e11a6c09a6
3
+ size 174112
latest ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75b0125738213c36e178c3103e033cd79fa6f44e0395ac68caf514fd7ec12315
3
+ size 16
merges.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
3
+ size 1671853
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe6b873f1da64bb980afe982fc1c6b6bc461ad8c33073d856804323f64b26d9
3
+ size 15429
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13db4dd10b22b5464f5ef0b539152b46390eae6a827b355108cb54b1af2eb830
3
+ size 15429
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e293f13fb6e873e8081636b6b07115410b397c55f1ed08b8772b059c8eb74e
3
+ size 15429
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c595c077664f94b7f91088561951be20e39483e01865774a83bc46f3971a3152
3
+ size 15429
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02b6aa96fb9be7384000b30bd129b4fb0d70feaf07e506249b8c2ecd76cd88e
3
+ size 1401
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
3
+ size 613
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06d54777a4c59c23ed608b2529c49f6a66853df9bc8a254d52eeb3b99d7c827
3
+ size 4712
trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bdf158847c43d16673b1f771a2aad57aa863a179791f90a16e49ce2a86039f
3
+ size 752458
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf8621c5541d1e60a09cd69d71abb7677782d7b635bed598ebdece3c2d78171
3
+ size 6161
vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a257b04b17642a0688c98cd1df89c398bda4fee532d6f88b38a659ecb4ac8d
3
+ size 3383407
zero_to_fp32.py ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46497565ccf2b4a8b1f6f18c8341042f3749605a94335c81f69df1bd268af64f
3
+ size 33272