Upload processor
Browse files- chat_template.jinja +2 -0
- processor_config.json +79 -0
- tokenizer.json +0 -0
- tokenizer_config.json +26 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
|
| 2 |
+
{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
|
processor_config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_image_splitting": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_pad": true,
|
| 7 |
+
"do_rescale": true,
|
| 8 |
+
"do_resize": true,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_processor_type": "SmolVLMImageProcessor",
|
| 15 |
+
"image_std": [
|
| 16 |
+
0.5,
|
| 17 |
+
0.5,
|
| 18 |
+
0.5
|
| 19 |
+
],
|
| 20 |
+
"max_image_size": {
|
| 21 |
+
"longest_edge": 384
|
| 22 |
+
},
|
| 23 |
+
"resample": 1,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"longest_edge": 1536
|
| 27 |
+
},
|
| 28 |
+
"video_sampling": {
|
| 29 |
+
"fps": 1,
|
| 30 |
+
"max_frames": 64,
|
| 31 |
+
"video_size": {
|
| 32 |
+
"longest_edge": 384
|
| 33 |
+
}
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"image_seq_len": 81,
|
| 37 |
+
"processor_class": "SmolVLMProcessor",
|
| 38 |
+
"video_processor": {
|
| 39 |
+
"data_format": "channels_first",
|
| 40 |
+
"default_to_square": true,
|
| 41 |
+
"do_convert_rgb": true,
|
| 42 |
+
"do_image_splitting": true,
|
| 43 |
+
"do_normalize": true,
|
| 44 |
+
"do_pad": true,
|
| 45 |
+
"do_rescale": true,
|
| 46 |
+
"do_resize": true,
|
| 47 |
+
"do_sample_frames": false,
|
| 48 |
+
"fps": 1,
|
| 49 |
+
"image_mean": [
|
| 50 |
+
0.5,
|
| 51 |
+
0.5,
|
| 52 |
+
0.5
|
| 53 |
+
],
|
| 54 |
+
"image_processor_type": "SmolVLMImageProcessor",
|
| 55 |
+
"image_std": [
|
| 56 |
+
0.5,
|
| 57 |
+
0.5,
|
| 58 |
+
0.5
|
| 59 |
+
],
|
| 60 |
+
"max_image_size": {
|
| 61 |
+
"longest_edge": 384
|
| 62 |
+
},
|
| 63 |
+
"num_frames": 64,
|
| 64 |
+
"resample": 1,
|
| 65 |
+
"rescale_factor": 0.00392156862745098,
|
| 66 |
+
"return_metadata": false,
|
| 67 |
+
"size": {
|
| 68 |
+
"longest_edge": 1536
|
| 69 |
+
},
|
| 70 |
+
"video_processor_type": "SmolVLMVideoProcessor",
|
| 71 |
+
"video_sampling": {
|
| 72 |
+
"fps": 1,
|
| 73 |
+
"max_frames": 64,
|
| 74 |
+
"video_size": {
|
| 75 |
+
"longest_edge": 1536
|
| 76 |
+
}
|
| 77 |
+
}
|
| 78 |
+
}
|
| 79 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|im_start|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"end_of_utterance_token": "<end_of_utterance>",
|
| 7 |
+
"eos_token": "<end_of_utterance>",
|
| 8 |
+
"fake_image_token": "<fake_token_around_image>",
|
| 9 |
+
"global_image_token": "<global-img>",
|
| 10 |
+
"image_token": "<image>",
|
| 11 |
+
"is_local": false,
|
| 12 |
+
"legacy": false,
|
| 13 |
+
"model_max_length": 16384,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"end_of_utterance_token": "<end_of_utterance>",
|
| 16 |
+
"fake_image_token": "<fake_token_around_image>",
|
| 17 |
+
"global_image_token": "<global-img>",
|
| 18 |
+
"image_token": "<image>"
|
| 19 |
+
},
|
| 20 |
+
"pad_token": "<|im_end|>",
|
| 21 |
+
"processor_class": "SmolVLMProcessor",
|
| 22 |
+
"tokenizer_class": "TokenizersBackend",
|
| 23 |
+
"truncation_side": "left",
|
| 24 |
+
"unk_token": "<|endoftext|>",
|
| 25 |
+
"vocab_size": 49152
|
| 26 |
+
}
|