Upload folder using huggingface_hub
Browse files- config.json +7 -4
- generation_config.json +1 -1
- tokenizer.json +7 -17
- tokenizer_config.json +3 -30
config.json
CHANGED
|
@@ -18,6 +18,7 @@
|
|
| 18 |
"num_attention_heads": 32,
|
| 19 |
"num_hidden_layers": 22,
|
| 20 |
"num_key_value_heads": 4,
|
|
|
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"quantization_config": {
|
| 23 |
"config_groups": {
|
|
@@ -70,13 +71,15 @@
|
|
| 70 |
"quantization_status": "compressed",
|
| 71 |
"sparsity_config": {},
|
| 72 |
"transform_config": {},
|
| 73 |
-
"version": "0.
|
| 74 |
},
|
| 75 |
"rms_norm_eps": 1e-05,
|
| 76 |
-
"
|
| 77 |
-
|
|
|
|
|
|
|
| 78 |
"tie_word_embeddings": false,
|
| 79 |
-
"transformers_version": "
|
| 80 |
"use_cache": true,
|
| 81 |
"vocab_size": 32000
|
| 82 |
}
|
|
|
|
| 18 |
"num_attention_heads": 32,
|
| 19 |
"num_hidden_layers": 22,
|
| 20 |
"num_key_value_heads": 4,
|
| 21 |
+
"pad_token_id": null,
|
| 22 |
"pretraining_tp": 1,
|
| 23 |
"quantization_config": {
|
| 24 |
"config_groups": {
|
|
|
|
| 71 |
"quantization_status": "compressed",
|
| 72 |
"sparsity_config": {},
|
| 73 |
"transform_config": {},
|
| 74 |
+
"version": "0.1.dev1+gc763417"
|
| 75 |
},
|
| 76 |
"rms_norm_eps": 1e-05,
|
| 77 |
+
"rope_parameters": {
|
| 78 |
+
"rope_theta": 10000.0,
|
| 79 |
+
"rope_type": "default"
|
| 80 |
+
},
|
| 81 |
"tie_word_embeddings": false,
|
| 82 |
+
"transformers_version": "5.8.0.dev0",
|
| 83 |
"use_cache": true,
|
| 84 |
"vocab_size": 32000
|
| 85 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"eos_token_id": 2,
|
| 4 |
"max_length": 2048,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "
|
| 7 |
}
|
|
|
|
| 3 |
"eos_token_id": 2,
|
| 4 |
"max_length": 2048,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "5.8.0.dev0"
|
| 7 |
}
|
tokenizer.json
CHANGED
|
@@ -31,23 +31,13 @@
|
|
| 31 |
"special": true
|
| 32 |
}
|
| 33 |
],
|
| 34 |
-
"normalizer":
|
| 35 |
-
|
| 36 |
-
"
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"type": "Replace",
|
| 43 |
-
"pattern": {
|
| 44 |
-
"String": " "
|
| 45 |
-
},
|
| 46 |
-
"content": "▁"
|
| 47 |
-
}
|
| 48 |
-
]
|
| 49 |
},
|
| 50 |
-
"pre_tokenizer": null,
|
| 51 |
"post_processor": {
|
| 52 |
"type": "TemplateProcessing",
|
| 53 |
"single": [
|
|
@@ -129,7 +119,7 @@
|
|
| 129 |
"model": {
|
| 130 |
"type": "BPE",
|
| 131 |
"dropout": null,
|
| 132 |
-
"unk_token":
|
| 133 |
"continuing_subword_prefix": null,
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
|
|
|
| 31 |
"special": true
|
| 32 |
}
|
| 33 |
],
|
| 34 |
+
"normalizer": null,
|
| 35 |
+
"pre_tokenizer": {
|
| 36 |
+
"type": "Metaspace",
|
| 37 |
+
"replacement": "▁",
|
| 38 |
+
"prepend_scheme": "first",
|
| 39 |
+
"split": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
},
|
|
|
|
| 41 |
"post_processor": {
|
| 42 |
"type": "TemplateProcessing",
|
| 43 |
"single": [
|
|
|
|
| 119 |
"model": {
|
| 120 |
"type": "BPE",
|
| 121 |
"dropout": null,
|
| 122 |
+
"unk_token": null,
|
| 123 |
"continuing_subword_prefix": null,
|
| 124 |
"end_of_word_suffix": null,
|
| 125 |
"fuse_unk": true,
|
tokenizer_config.json
CHANGED
|
@@ -1,38 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
"add_prefix_space": null,
|
| 5 |
-
"
|
| 6 |
-
"0": {
|
| 7 |
-
"content": "<unk>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"1": {
|
| 15 |
-
"content": "<s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": true
|
| 21 |
-
},
|
| 22 |
-
"2": {
|
| 23 |
-
"content": "</s>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": true
|
| 29 |
-
}
|
| 30 |
-
},
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
"model_max_length": 2048,
|
| 37 |
"pad_token": "</s>",
|
| 38 |
"padding_side": "right",
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": "<s>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
"model_max_length": 2048,
|
| 10 |
"pad_token": "</s>",
|
| 11 |
"padding_side": "right",
|