Upload folder using huggingface_hub
Browse files- chat_template.jinja +4 -0
- tokenizer.json +0 -0
- tokenizer_config.json +83 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '
|
| 2 |
+
' + message['content'] + '<|im_end|>
|
| 3 |
+
' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
+
' }}{% endif %}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|bos|>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<|eos|>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<|unk|>",
|
| 8 |
+
"<|pad|>",
|
| 9 |
+
"<|bos|>",
|
| 10 |
+
"<|eos|>",
|
| 11 |
+
"<|mask|>",
|
| 12 |
+
"<|im_start|>",
|
| 13 |
+
"<|im_end|>",
|
| 14 |
+
"<|system|>",
|
| 15 |
+
"<|user|>",
|
| 16 |
+
"<|assistant|>",
|
| 17 |
+
"<think>",
|
| 18 |
+
"</think>",
|
| 19 |
+
"<|begin_of_thought|>",
|
| 20 |
+
"<|end_of_thought|>",
|
| 21 |
+
"<answer>",
|
| 22 |
+
"</answer>",
|
| 23 |
+
"<|step|>",
|
| 24 |
+
"<|/step|>",
|
| 25 |
+
"<context>",
|
| 26 |
+
"</context>",
|
| 27 |
+
"<|doc_start|>",
|
| 28 |
+
"<|doc_end|>",
|
| 29 |
+
"<|search|>",
|
| 30 |
+
"<|search_results|>",
|
| 31 |
+
"<|tool_list_start|>",
|
| 32 |
+
"<|tool_list_end|>",
|
| 33 |
+
"<tools>",
|
| 34 |
+
"</tools>",
|
| 35 |
+
"<|tool_call_start|>",
|
| 36 |
+
"<|tool_call_end|>",
|
| 37 |
+
"<|tool_call|>",
|
| 38 |
+
"<|/tool_call|>",
|
| 39 |
+
"<|tool_response_start|>",
|
| 40 |
+
"<|tool_response_end|>",
|
| 41 |
+
"<|tool_response|>",
|
| 42 |
+
"<|/tool_response|>",
|
| 43 |
+
"<|image|>",
|
| 44 |
+
"<|image_pad|>",
|
| 45 |
+
"<|image_placeholder|>",
|
| 46 |
+
"<|audio|>",
|
| 47 |
+
"<|audio_pad|>",
|
| 48 |
+
"<|audio_placeholder|>",
|
| 49 |
+
"<|video|>",
|
| 50 |
+
"<|video_pad|>",
|
| 51 |
+
"<|fim_prefix|>",
|
| 52 |
+
"<|fim_suffix|>",
|
| 53 |
+
"<|fim_middle|>",
|
| 54 |
+
"<|repo_name|>",
|
| 55 |
+
"<|file_separator|>",
|
| 56 |
+
"<|reward|>",
|
| 57 |
+
"<|reserved_0|>",
|
| 58 |
+
"<|reserved_1|>",
|
| 59 |
+
"<|reserved_2|>",
|
| 60 |
+
"<|reserved_3|>",
|
| 61 |
+
"<|reserved_4|>",
|
| 62 |
+
"<|reserved_5|>",
|
| 63 |
+
"<|reserved_6|>",
|
| 64 |
+
"<|reserved_7|>",
|
| 65 |
+
"<|reserved_8|>",
|
| 66 |
+
"<|reserved_9|>",
|
| 67 |
+
"<|reserved_10|>",
|
| 68 |
+
"<|reserved_11|>",
|
| 69 |
+
"<|reserved_12|>",
|
| 70 |
+
"<|reserved_13|>",
|
| 71 |
+
"<|reserved_14|>",
|
| 72 |
+
"<|reserved_15|>",
|
| 73 |
+
"<|reserved_16|>",
|
| 74 |
+
"<|reserved_17|>",
|
| 75 |
+
"<|reserved_18|>",
|
| 76 |
+
"<|reserved_19|>"
|
| 77 |
+
],
|
| 78 |
+
"mask_token": "<|mask|>",
|
| 79 |
+
"model_max_length": 8192,
|
| 80 |
+
"pad_token": "<|pad|>",
|
| 81 |
+
"tokenizer_class": "TokenizersBackend",
|
| 82 |
+
"unk_token": "<|unk|>"
|
| 83 |
+
}
|