Hugging Face's logo

mT0
/
mt0_large_translated_t0_ckpt_1025000

Text2Text Generation
Transformers
PyTorch
mt5
Inference Endpoints
Model card Files Community
Lintang Sutawika commited on
Commit
21b2dcd
•
1 Parent(s): d80edf9

added mt0 large trained on translated t0 up to 25000 steps

Browse files
Files changed (18) hide show
  1. config.json +30 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state_0.pth +3 -0
  5. rng_state_1.pth +3 -0
  6. rng_state_2.pth +3 -0
  7. rng_state_3.pth +3 -0
  8. rng_state_4.pth +3 -0
  9. rng_state_5.pth +3 -0
  10. rng_state_6.pth +3 -0
  11. rng_state_7.pth +3 -0
  12. scaler.pt +3 -0
  13. scheduler.pt +3 -0
  14. special_tokens_map.json +1 -0
  15. spiece.model +3 -0
  16. tokenizer_config.json +1 -0
  17. trainer_state.json +0 -0
  18. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-large",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "mt5",
17
+ "num_decoder_layers": 24,
18
+ "num_heads": 16,
19
+ "num_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_max_distance": 128,
23
+ "relative_attention_num_buckets": 32,
24
+ "tie_word_embeddings": false,
25
+ "tokenizer_class": "T5Tokenizer",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.18.0",
28
+ "use_cache": true,
29
+ "vocab_size": 250100
30
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9c4be8d636f5b44b8f8a62a4e9465cbbf689bd749766054160f05cc1f05ed7
3
+ size 7516745
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803b75663d4e20817df1da3bb4b9111ddd68cdb93fa6087d1175d2693c65e565
3
+ size 4918417209
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4504bca6f3d1eae87e7edfa08a0ba4e4bf8065b6fb66b5a6ce2b8051acb40
3
+ size 14503
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4504bca6f3d1eae87e7edfa08a0ba4e4bf8065b6fb66b5a6ce2b8051acb40
3
+ size 14503
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4504bca6f3d1eae87e7edfa08a0ba4e4bf8065b6fb66b5a6ce2b8051acb40
3
+ size 14503
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4504bca6f3d1eae87e7edfa08a0ba4e4bf8065b6fb66b5a6ce2b8051acb40
3
+ size 14503
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4504bca6f3d1eae87e7edfa08a0ba4e4bf8065b6fb66b5a6ce2b8051acb40
3
+ size 14503
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4504bca6f3d1eae87e7edfa08a0ba4e4bf8065b6fb66b5a6ce2b8051acb40
3
+ size 14503
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4504bca6f3d1eae87e7edfa08a0ba4e4bf8065b6fb66b5a6ce2b8051acb40
3
+ size 14503
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e4504bca6f3d1eae87e7edfa08a0ba4e4bf8065b6fb66b5a6ce2b8051acb40
3
+ size 14503
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1faccae0f0d206d57b35c1c1890f46b90baa0cb44a0a8199c80a2a400f4f6f64
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c418e8c846e8f3f9a843ae8ba0703ef6ae334354df9a350830e4a697885a12ff
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-large", "tokenizer_class": "T5Tokenizer"}
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d794296ebcb8a39c0592a594f25c0d3a07c34e0e19e3b71603507b761e75dc6
3
+ size 3247