Hugging Face's logo

Itaking
/
itakura_v4-model

Text Generation
Safetensors
English
Japanese
olmo2
olmo
causal-lm
bilingual
japanese
from-scratch
conversational
Model card Files
xet
 Community
Itaking commited on
Commit
57a2ebf
·
verified ·
1 Parent(s): 4fb4da3

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. checkpoint-3801/config.json +28 -0
  2. checkpoint-3801/generation_config.json +7 -0
  3. checkpoint-3801/model.safetensors +3 -0
  4. checkpoint-3801/optimizer.pt +3 -0
  5. checkpoint-3801/rng_state.pth +3 -0
  6. checkpoint-3801/scheduler.pt +3 -0
  7. checkpoint-3801/special_tokens_map.json +35 -0
  8. checkpoint-3801/tokenizer.json +0 -0
  9. checkpoint-3801/tokenizer_config.json +58 -0
  10. checkpoint-3801/trainer_state.json +0 -0
  11. checkpoint-3801/training_args.bin +3 -0
  12. config.json +28 -0
  13. generation_config.json +7 -0
  14. model.safetensors +3 -0
  15. special_tokens_map.json +35 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +58 -0
  18. training_args.bin +3 -0
checkpoint-3801/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/sft",
3
+ "architectures": [
4
+ "Olmo2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "olmo2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 16,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.47.0",
26
+ "use_cache": false,
27
+ "vocab_size": 65536
28
+ }
checkpoint-3801/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.47.0"
7
+ }
checkpoint-3801/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c835569fc6868581fcb1a71c0fcbef34a4d650c31e3ca5e414cb358adb32e26
3
+ size 771889040
checkpoint-3801/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f76f8e03ed1a9ce329c7c9bcbaa0e4c59f3ad13e5b81731ee889695b116cdc
3
+ size 1543887930
checkpoint-3801/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
checkpoint-3801/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11199a2056eae24a7b539975c36ca618910c6dd69adada7b32cafa7546a58268
3
+ size 1064
checkpoint-3801/special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|user|>",
4
+ "<|assistant|>",
5
+ "<|system|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|endoftext|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<|padding|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
checkpoint-3801/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3801/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|user|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|assistant|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|system|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "<|user|>",
46
+ "<|assistant|>",
47
+ "<|system|>"
48
+ ],
49
+ "bos_token": "<|endoftext|>",
50
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|system|>\n{{ message['content'] }}\n{% elif message['role'] == 'user' %}<|user|>\n{{ message['content'] }}\n{% elif message['role'] == 'assistant' %}<|assistant|>\n{{ message['content'] }}{{ eos_token }}\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>\n{% endif %}",
51
+ "clean_up_tokenization_spaces": false,
52
+ "eos_token": "<|endoftext|>",
53
+ "extra_special_tokens": {},
54
+ "model_max_length": 1000000000000000019884624838656,
55
+ "pad_token": "<|padding|>",
56
+ "tokenizer_class": "PreTrainedTokenizerFast",
57
+ "unk_token": "<|endoftext|>"
58
+ }
checkpoint-3801/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3801/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af42ef9bfcda66ea7d72451bdfc9db238c592215d63e2850bd2f59c36d29b64a
3
+ size 6200
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/sft",
3
+ "architectures": [
4
+ "Olmo2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "olmo2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 16,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.47.0",
26
+ "use_cache": false,
27
+ "vocab_size": 65536
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.47.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c835569fc6868581fcb1a71c0fcbef34a4d650c31e3ca5e414cb358adb32e26
3
+ size 771889040
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|user|>",
4
+ "<|assistant|>",
5
+ "<|system|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|endoftext|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<|padding|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|user|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|assistant|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|system|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "<|user|>",
46
+ "<|assistant|>",
47
+ "<|system|>"
48
+ ],
49
+ "bos_token": "<|endoftext|>",
50
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|system|>\n{{ message['content'] }}\n{% elif message['role'] == 'user' %}<|user|>\n{{ message['content'] }}\n{% elif message['role'] == 'assistant' %}<|assistant|>\n{{ message['content'] }}{{ eos_token }}\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>\n{% endif %}",
51
+ "clean_up_tokenization_spaces": false,
52
+ "eos_token": "<|endoftext|>",
53
+ "extra_special_tokens": {},
54
+ "model_max_length": 1000000000000000019884624838656,
55
+ "pad_token": "<|padding|>",
56
+ "tokenizer_class": "PreTrainedTokenizerFast",
57
+ "unk_token": "<|endoftext|>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af42ef9bfcda66ea7d72451bdfc9db238c592215d63e2850bd2f59c36d29b64a
3
+ size 6200