Hugging Face's logo

xiaoyewuz-Ruster
/
zzjrabbit3-pre2

Safetensors
Model card Files
xet
 Community
xiaoyewuz-Ruster commited on
Commit
3a0dae7
·
verified ·
1 Parent(s): 1910a3e

Add files using upload-large-folder tool

Browse files
Files changed (32) hide show
  1. checkpoint-81500/config.json +16 -0
  2. checkpoint-81500/generation_config.json +8 -0
  3. checkpoint-81500/model.safetensors +3 -0
  4. checkpoint-81500/optimizer.pt +3 -0
  5. checkpoint-81500/rng_state.pth +3 -0
  6. checkpoint-81500/scheduler.pt +3 -0
  7. checkpoint-81500/tokenizer.json +0 -0
  8. checkpoint-81500/tokenizer_config.json +15 -0
  9. checkpoint-81500/trainer_state.json +0 -0
  10. checkpoint-81500/training_args.bin +3 -0
  11. checkpoint-82000/config.json +16 -0
  12. checkpoint-82000/generation_config.json +8 -0
  13. checkpoint-82000/model.safetensors +3 -0
  14. checkpoint-82000/optimizer.pt +3 -0
  15. checkpoint-82000/rng_state.pth +3 -0
  16. checkpoint-82000/scheduler.pt +3 -0
  17. checkpoint-82000/tokenizer.json +0 -0
  18. checkpoint-82000/tokenizer_config.json +15 -0
  19. checkpoint-82000/trainer_state.json +0 -0
  20. checkpoint-82000/training_args.bin +3 -0
  21. checkpoint-82500/config.json +16 -0
  22. checkpoint-82500/generation_config.json +8 -0
  23. checkpoint-82500/model.safetensors +3 -0
  24. checkpoint-82500/optimizer.pt +3 -0
  25. checkpoint-82500/rng_state.pth +3 -0
  26. checkpoint-82500/scheduler.pt +3 -0
  27. checkpoint-82500/tokenizer.json +0 -0
  28. checkpoint-82500/tokenizer_config.json +15 -0
  29. checkpoint-82500/trainer_state.json +0 -0
  30. checkpoint-82500/training_args.bin +3 -0
  31. checkpoint-83000/config.json +16 -0
  32. checkpoint-83000/generation_config.json +8 -0
checkpoint-81500/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ZZJRabbit3ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "float32",
7
+ "eos_token_id": 0,
8
+ "hidden_size": 1024,
9
+ "model_type": "zzjrabbit3",
10
+ "num_attention_heads": 8,
11
+ "num_hidden_layers": 12,
12
+ "pad_token_id": 0,
13
+ "transformers_version": "5.3.0",
14
+ "use_cache": false,
15
+ "vocab_size": 100000
16
+ }
checkpoint-81500/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "output_attentions": false,
5
+ "output_hidden_states": false,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "5.3.0"
8
+ }
checkpoint-81500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef1314232aa17c2629d84b54e4f99bea8b937bd355a0ea66c47f169e767e514
3
+ size 1122999520
checkpoint-81500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e0a734547626024035ac58e85a7c112aa2753e54c587caa5763772cedf66c60
3
+ size 2244001739
checkpoint-81500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94b7483e4d38829c92a7b7bf3db04a009bcf1e17da7d110a281b848daa1f1a2
3
+ size 14645
checkpoint-81500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fabde792049bd53601704b41b67f1583aa9762c73dc3c06f2b0eee9811a1fbd
3
+ size 1465
checkpoint-81500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-81500/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "zzjrabbit3.ZZJRabbit3Tokenizer",
5
+ null
6
+ ]
7
+ },
8
+ "backend": "tokenizers",
9
+ "eos_token": "<eos>",
10
+ "is_local": true,
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "<eos>",
13
+ "tokenizer_class": "ZZJRabbit3Tokenizer",
14
+ "unk_token": "<eos>"
15
+ }
checkpoint-81500/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-81500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f609109a58c67ca94b9bacee640d9e4d2bfaa7c2c49afe1c564ac4e015cfc542
3
+ size 5201
checkpoint-82000/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ZZJRabbit3ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "float32",
7
+ "eos_token_id": 0,
8
+ "hidden_size": 1024,
9
+ "model_type": "zzjrabbit3",
10
+ "num_attention_heads": 8,
11
+ "num_hidden_layers": 12,
12
+ "pad_token_id": 0,
13
+ "transformers_version": "5.3.0",
14
+ "use_cache": false,
15
+ "vocab_size": 100000
16
+ }
checkpoint-82000/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "output_attentions": false,
5
+ "output_hidden_states": false,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "5.3.0"
8
+ }
checkpoint-82000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c0691aa2fadf6cb66dbe3b387433e8fdd2bf28fd093870c501ee3f1e3e8992
3
+ size 1122999520
checkpoint-82000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13df015bcf36c1430171c29fe2f86d15d54fed020dc2d3e5d21a5874fa947208
3
+ size 2244001739
checkpoint-82000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa470922c6bb65dee2b176c94e1ac5b1a48d8825edcb64f132565292131966c4
3
+ size 14645
checkpoint-82000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48dc71cdbc0de82b20c1c70ec2c6e8641da5f316948dac99e124f6a948aed961
3
+ size 1465
checkpoint-82000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-82000/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "zzjrabbit3.ZZJRabbit3Tokenizer",
5
+ null
6
+ ]
7
+ },
8
+ "backend": "tokenizers",
9
+ "eos_token": "<eos>",
10
+ "is_local": true,
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "<eos>",
13
+ "tokenizer_class": "ZZJRabbit3Tokenizer",
14
+ "unk_token": "<eos>"
15
+ }
checkpoint-82000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-82000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f609109a58c67ca94b9bacee640d9e4d2bfaa7c2c49afe1c564ac4e015cfc542
3
+ size 5201
checkpoint-82500/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ZZJRabbit3ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "float32",
7
+ "eos_token_id": 0,
8
+ "hidden_size": 1024,
9
+ "model_type": "zzjrabbit3",
10
+ "num_attention_heads": 8,
11
+ "num_hidden_layers": 12,
12
+ "pad_token_id": 0,
13
+ "transformers_version": "5.3.0",
14
+ "use_cache": false,
15
+ "vocab_size": 100000
16
+ }
checkpoint-82500/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "output_attentions": false,
5
+ "output_hidden_states": false,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "5.3.0"
8
+ }
checkpoint-82500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b244042af880bbb439cb7d6451dd11f8182b035ffdeb50f6b33305700918601
3
+ size 1122999520
checkpoint-82500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ba7c1b3122bc5472fb61f33f15fd0d9ebcb9c7d8c0aa70ac47c86b23529ee0
3
+ size 2244001739
checkpoint-82500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c122836c560242699681afbe59ff5403879609ca3f880cd8f706d36b7f937573
3
+ size 14645
checkpoint-82500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3a009ccdfacc6cff031fc01127ad5b6261888d0ccbab182fd9add369f23d3a
3
+ size 1465
checkpoint-82500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-82500/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "zzjrabbit3.ZZJRabbit3Tokenizer",
5
+ null
6
+ ]
7
+ },
8
+ "backend": "tokenizers",
9
+ "eos_token": "<eos>",
10
+ "is_local": true,
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "<eos>",
13
+ "tokenizer_class": "ZZJRabbit3Tokenizer",
14
+ "unk_token": "<eos>"
15
+ }
checkpoint-82500/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-82500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f609109a58c67ca94b9bacee640d9e4d2bfaa7c2c49afe1c564ac4e015cfc542
3
+ size 5201
checkpoint-83000/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ZZJRabbit3ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "float32",
7
+ "eos_token_id": 0,
8
+ "hidden_size": 1024,
9
+ "model_type": "zzjrabbit3",
10
+ "num_attention_heads": 8,
11
+ "num_hidden_layers": 12,
12
+ "pad_token_id": 0,
13
+ "transformers_version": "5.3.0",
14
+ "use_cache": false,
15
+ "vocab_size": 100000
16
+ }
checkpoint-83000/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "output_attentions": false,
5
+ "output_hidden_states": false,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "5.3.0"
8
+ }