Hugging Face's logo

ysn-rfd
/
YASIN-Persian-Base

Text Generation
Safetensors
Persian
yasin
persian
decoder-only
Model card Files
xet
Community
1
ysn-rfd commited on
Commit
b81c6b6
·
verified ·
1 Parent(s): 44ddf21

آپلود مدل YASIN آموزش دیده روی داده‌های فارسی

Browse files
Files changed (18) hide show
  1. added_tokens.json +6 -0
  2. best_model/added_tokens.json +6 -0
  3. best_model/config.json +30 -0
  4. best_model/generation_config.json +7 -0
  5. best_model/merges.txt +0 -0
  6. best_model/model.safetensors +3 -0
  7. best_model/special_tokens_map.json +40 -0
  8. best_model/tokenizer.json +0 -0
  9. best_model/tokenizer_config.json +57 -0
  10. best_model/vocab.json +0 -0
  11. config.json +30 -0
  12. generation_config.json +7 -0
  13. merges.txt +0 -0
  14. model.safetensors +3 -0
  15. special_tokens_map.json +40 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +57 -0
  18. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "### سوال:": 50259,
3
+ "### پاسخ:": 50260,
4
+ "</s>": 50258,
5
+ "<s>": 50257
6
+ }
best_model/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "### سوال:": 50259,
3
+ "### پاسخ:": 50260,
4
+ "</s>": 50258,
5
+ "<s>": 50257
6
+ }
best_model/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "YasinForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": 50257,
8
+ "dtype": "float32",
9
+ "eos_token_id": 50258,
10
+ "head_dim": 48,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_position_embeddings": 512,
16
+ "mlp_bias": false,
17
+ "model_type": "yasin",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 16,
21
+ "pad_token_id": 50256,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "transformers_version": "4.57.3",
28
+ "use_cache": true,
29
+ "vocab_size": 50261
30
+ }
best_model/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50257,
4
+ "eos_token_id": 50258,
5
+ "pad_token_id": 50256,
6
+ "transformers_version": "4.57.3"
7
+ }
best_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb56c3fb13f6b9cf16bde85d1bc15ed5a6e1d9c91aab58e7dc5cf9598f4dfee
3
+ size 912901088
best_model/special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "### سوال:",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "### پاسخ:",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "unk_token": "<|endoftext|>"
40
+ }
best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
best_model/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "### سوال:",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "### پاسخ:",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [
46
+ "### سوال:",
47
+ "### پاسخ:"
48
+ ],
49
+ "bos_token": "<s>",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "</s>",
52
+ "extra_special_tokens": {},
53
+ "model_max_length": 1024,
54
+ "pad_token": "<|endoftext|>",
55
+ "tokenizer_class": "GPT2Tokenizer",
56
+ "unk_token": "<|endoftext|>"
57
+ }
best_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "YasinForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": 50257,
8
+ "dtype": "float32",
9
+ "eos_token_id": 50258,
10
+ "head_dim": 48,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_position_embeddings": 512,
16
+ "mlp_bias": false,
17
+ "model_type": "yasin",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 16,
21
+ "pad_token_id": 50256,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "transformers_version": "4.57.3",
28
+ "use_cache": true,
29
+ "vocab_size": 50261
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50257,
4
+ "eos_token_id": 50258,
5
+ "pad_token_id": 50256,
6
+ "transformers_version": "4.57.3"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb56c3fb13f6b9cf16bde85d1bc15ed5a6e1d9c91aab58e7dc5cf9598f4dfee
3
+ size 912901088
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "### سوال:",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "### پاسخ:",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "unk_token": "<|endoftext|>"
40
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "### سوال:",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "### پاسخ:",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [
46
+ "### سوال:",
47
+ "### پاسخ:"
48
+ ],
49
+ "bos_token": "<s>",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "</s>",
52
+ "extra_special_tokens": {},
53
+ "model_max_length": 1024,
54
+ "pad_token": "<|endoftext|>",
55
+ "tokenizer_class": "GPT2Tokenizer",
56
+ "unk_token": "<|endoftext|>"
57
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff