upload tokenizer files from KnutJaegersberg/Qwen-14B-Llamafied
Browse files- generation_config.json +12 -0
- merges.txt +0 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +9 -0
- vocab.json +0 -0
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_format": "chatml",
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 151643,
|
5 |
+
"max_new_tokens": 512,
|
6 |
+
"max_window_size": 6144,
|
7 |
+
"pad_token_id": 151643,
|
8 |
+
"repetition_penalty": 1.1,
|
9 |
+
"top_k": 0,
|
10 |
+
"top_p": 0.8,
|
11 |
+
"transformers_version": "4.34.1"
|
12 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": "<|endoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"tokenizer_class": "GPT2Tokenizer",
|
5 |
+
"clean_up_tokenization_spaces": true,
|
6 |
+
"eos_token": "<|endoftext|>",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|