Hugging Face's logo

Finnish-NLP
/
t5-large-nl36-finnish

Text2Text Generation
Transformers
PyTorch
JAX
TensorBoard
Finnish
t5
finnish
t5x
seq2seq
text-generation-inference
Model card Files Metrics Community
aapot commited on
Commit
85e37ee
•
1 Parent(s): c7b19f5

Add 10k step

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint_10000/checkpoint +3 -0
  2. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.decoder_norm.scale.v/.zarray +0 -0
  3. checkpoint_10000/state.param_states.decoder.decoder_norm.scale.v/0 +3 -0
  4. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray +0 -0
  5. checkpoint_10000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  6. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray +0 -0
  7. checkpoint_10000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/0 +3 -0
  8. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray +0 -0
  9. checkpoint_10000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 +3 -0
  10. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray +0 -0
  11. checkpoint_10000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  12. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray +0 -0
  13. checkpoint_10000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/0 +3 -0
  14. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray +0 -0
  15. checkpoint_10000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/0 +3 -0
  16. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/.zarray +0 -0
  17. checkpoint_10000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  18. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray +0 -0
  19. checkpoint_10000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/0 +3 -0
  20. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/.zarray +0 -0
  21. checkpoint_10000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/0 +3 -0
  22. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/.zarray +0 -0
  23. checkpoint_10000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  24. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray +0 -0
  25. checkpoint_10000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/0 +3 -0
  26. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray +0 -0
  27. checkpoint_10000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/0 +3 -0
  28. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/.zarray +0 -0
  29. checkpoint_10000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  30. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/.zarray +0 -0
  31. checkpoint_10000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/0 +3 -0
  32. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/.zarray +0 -0
  33. checkpoint_10000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/0 +3 -0
  34. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray +0 -0
  35. checkpoint_10000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  36. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray +0 -0
  37. checkpoint_10000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/0 +3 -0
  38. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/.zarray +0 -0
  39. checkpoint_10000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/0 +3 -0
  40. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/.zarray +0 -0
  41. checkpoint_10000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  42. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/.zarray +0 -0
  43. checkpoint_10000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/0 +3 -0
  44. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/.zarray +0 -0
  45. checkpoint_10000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/0 +3 -0
  46. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/.zarray +0 -0
  47. checkpoint_10000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  48. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/.zarray +0 -0
  49. checkpoint_10000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/0 +3 -0
  50. {checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_15.pre_self_attention_layer_norm.scale.v/.zarray +0 -0
checkpoint_10000/checkpoint ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c1d80981590b80b85f50d8a6a502c5ab66e2eff753460a1f09a3c051b21bca
3
+ size 8513341
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.decoder_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.decoder_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa5d74e14e575f6ad32b3091f070b7e7feca9c23b77fd0ce7f1a6b600c38cbc7
3
+ size 3618
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89048efe22dde611ad78f174ee35e4d9c68464dfb7b3d491480d02dc8b6002f3
3
+ size 3630
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91278f025a15f7eae9fc91e6e8412c91109697d6bbab5a84020410a5b7db1b73
3
+ size 3487
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:692c5b4832a37491b1fdb050e8a6415902368fecdffdef7ed1f7d73c98fdea40
3
+ size 3555
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49cbbcbe1ecf473401ad3633218148eaf39d9ed272ed069e33a703e8c3d67b9
3
+ size 3590
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da0bb2091dbb00e2001b5f3f723135017ffcaa8adc3a66b247e44a155db49b5
3
+ size 3538
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b1c2196f20ec5b2fb80b81b8e3a10a9a10ea23445ffdaedc1e95ba21cb5f60
3
+ size 3605
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_10.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a1aa45eee8b453e9d47162c871151c6b3067ff51f24fe1d2141439ba7589092
3
+ size 3665
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_10.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb3f45754b208fbc765c44b6df04c4789f0f908b64fc4f9c8be891fd79590ca
3
+ size 3600
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_10.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e45cb21794f9e1daf1d362d3015d608edde2d536a195d32206ddb72df0387d
3
+ size 3591
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_11.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe7e648b9673edd40b3c007ed527e0231f8942448eb85873a603bf837f950d2
3
+ size 3662
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_11.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91abfbd6a800f97eeb8535c7a2153f7e47e9069c3318a34accba7e8982aa8580
3
+ size 3613
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_11.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2a99d5e5a98292a424e17bf01b4ddafd3881ca383c26ee3b5f8b0de7943441
3
+ size 3624
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_12.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43925492f667ed6f62a11677555a39aed43e5459d602c9e6848dd5f66e22a77f
3
+ size 3669
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_12.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d303c961e8acb0331001a37763558b5e73e088f1fa00a2c260083de0deef26
3
+ size 3639
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_12.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ad62a8818d95dfd4cc19a57360dac37c562950a231ad2146e333ab4812e549
3
+ size 3582
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_13.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3eb348dd7528cfbf1e8e7c0def5feb501a2f7a78ae116a39133453288f13aa
3
+ size 3647
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_13.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beeffb67fb9af4194f63119ea5c0e4ba80905fba752f70a0956326e627b0e109
3
+ size 3647
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_13.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1884dc19f2659d72bf249e5984bd8cd790d5c69da5f838418f57908eb10d9ff4
3
+ size 3645
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_14.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda46c4739fc6029b057c15178551c0c9b610fc8723e7fb0f7c2f93656eeee9a
3
+ size 3666
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_14.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8712722c6737a0508c4d657e69217fd8ddb2db3829cbe2830a5b8ec4fbfc0d4d
3
+ size 3637
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_14.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3139adaad021dd7c0b6fde8124e6fb066adf252e6e0555aa2dc6eca7918e07
3
+ size 3575
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_15.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52b9ca316a17695627d19cbd45eb64a094e1d7b2825d4fbf23775b62c961b456
3
+ size 3671
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/.zarray RENAMED
File without changes
checkpoint_10000/state.param_states.decoder.layers_15.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5baebfd4d8a1205b897309de2031a798d1b07bbd65cbda2287e3676c63a4f15d
3
+ size 3631
{checkpoint_100000 → checkpoint_10000}/state.param_states.decoder.layers_15.pre_self_attention_layer_norm.scale.v/.zarray RENAMED
File without changes