mylesgoose
commited on
Commit
•
8fa247a
1
Parent(s):
1970389
Upload 5 files
Browse files- config.json +5 -1
- generation_config.json +8 -1
- special_tokens_map.json +8 -1
- tokenizer_config.json +4 -3
config.json
CHANGED
@@ -6,7 +6,11 @@
|
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
10 |
"head_dim": 128,
|
11 |
"hidden_act": "silu",
|
12 |
"hidden_size": 3072,
|
|
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
"head_dim": 128,
|
15 |
"hidden_act": "silu",
|
16 |
"hidden_size": 3072,
|
generation_config.json
CHANGED
@@ -1,6 +1,13 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"bos_token_id": 128000,
|
4 |
-
"
|
|
|
5 |
"transformers_version": "4.45.0.dev0"
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
"bos_token_id": 128000,
|
10 |
+
"temperature": 0.9,
|
11 |
+
"top_p": 0.9,
|
12 |
"transformers_version": "4.45.0.dev0"
|
13 |
}
|
special_tokens_map.json
CHANGED
@@ -7,7 +7,14 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "<|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|finetune_right_pad_id|>",
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -2050,14 +2050,15 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
-
"eos_token": "<|
|
2055 |
"model_input_names": [
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
"model_max_length": 131072,
|
2060 |
-
"pad_token": "<|
|
2061 |
-
"
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
2062 |
+
"padding_side": "right",
|
2063 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2064 |
}
|