fix bos, eos token id
Browse files- config.json +3 -3
- pytorch_model.bin +3 -0
- special_tokens_map.json +3 -3
- tokenizer_config.json +3 -3
config.json
CHANGED
|
@@ -4,9 +4,9 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
"end_token_id": 100257,
|
| 9 |
-
"eos_token_id":
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 1024,
|
|
@@ -29,4 +29,4 @@
|
|
| 29 |
"transformers_version": "4.50.3",
|
| 30 |
"use_cache": false,
|
| 31 |
"vocab_size": 110592
|
| 32 |
-
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100272,
|
| 8 |
"end_token_id": 100257,
|
| 9 |
+
"eos_token_id": 100273,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 1024,
|
|
|
|
| 29 |
"transformers_version": "4.50.3",
|
| 30 |
"use_cache": false,
|
| 31 |
"vocab_size": 110592
|
| 32 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:decbc37141e9bc7b88f38395070c5261d9b68029973dfd3f3b63380c6165a8f4
|
| 3 |
+
size 1132633202
|
special_tokens_map.json
CHANGED
|
@@ -56,14 +56,14 @@
|
|
| 56 |
"<PASSWORD>"
|
| 57 |
],
|
| 58 |
"bos_token": {
|
| 59 |
-
"content": "<|
|
| 60 |
"lstrip": false,
|
| 61 |
"normalized": false,
|
| 62 |
"rstrip": false,
|
| 63 |
"single_word": false
|
| 64 |
},
|
| 65 |
"eos_token": {
|
| 66 |
-
"content": "<|
|
| 67 |
"lstrip": false,
|
| 68 |
"normalized": false,
|
| 69 |
"rstrip": false,
|
|
@@ -83,4 +83,4 @@
|
|
| 83 |
"rstrip": false,
|
| 84 |
"single_word": false
|
| 85 |
}
|
| 86 |
-
}
|
|
|
|
| 56 |
"<PASSWORD>"
|
| 57 |
],
|
| 58 |
"bos_token": {
|
| 59 |
+
"content": "<|im_start|>",
|
| 60 |
"lstrip": false,
|
| 61 |
"normalized": false,
|
| 62 |
"rstrip": false,
|
| 63 |
"single_word": false
|
| 64 |
},
|
| 65 |
"eos_token": {
|
| 66 |
+
"content": "<|im_end|>",
|
| 67 |
"lstrip": false,
|
| 68 |
"normalized": false,
|
| 69 |
"rstrip": false,
|
|
|
|
| 83 |
"rstrip": false,
|
| 84 |
"single_word": false
|
| 85 |
}
|
| 86 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -490,13 +490,13 @@
|
|
| 490 |
"<KEY>",
|
| 491 |
"<PASSWORD>"
|
| 492 |
],
|
| 493 |
-
"bos_token": "<|
|
| 494 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 495 |
"clean_up_tokenization_spaces": true,
|
| 496 |
-
"eos_token": "<|
|
| 497 |
"extra_special_tokens": {},
|
| 498 |
"model_max_length": 1000000000000000019884624838656,
|
| 499 |
"pad_token": "<|endoftext|>",
|
| 500 |
"tokenizer_class": "GPT2Tokenizer",
|
| 501 |
"unk_token": "<|endoftext|>"
|
| 502 |
-
}
|
|
|
|
| 490 |
"<KEY>",
|
| 491 |
"<PASSWORD>"
|
| 492 |
],
|
| 493 |
+
"bos_token": "<|im_start|>",
|
| 494 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 495 |
"clean_up_tokenization_spaces": true,
|
| 496 |
+
"eos_token": "<|im_end|>",
|
| 497 |
"extra_special_tokens": {},
|
| 498 |
"model_max_length": 1000000000000000019884624838656,
|
| 499 |
"pad_token": "<|endoftext|>",
|
| 500 |
"tokenizer_class": "GPT2Tokenizer",
|
| 501 |
"unk_token": "<|endoftext|>"
|
| 502 |
+
}
|