Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +1 -0
- config.json +6 -0
- generation_config.json +14 -0
- inference.yml +3 -0
- merges.txt +0 -0
- model_state.pdparams +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
model_state.pdparams filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<|endoftext|>": 151643, "<|im_start|>": 151644, "<|im_end|>": 151645, "<|object_ref_start|>": 151646, "<|object_ref_end|>": 151647, "<|box_start|>": 151648, "<|box_end|>": 151649, "<|quad_start|>": 151650, "<|quad_end|>": 151651, "<|vision_start|>": 151652, "<|vision_end|>": 151653, "<|vision_pad|>": 151654, "<|image_pad|>": 151655, "<|video_pad|>": 151656}
|
config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"mode": "paddle",
|
3 |
+
"Global": {
|
4 |
+
"model_name": "PP-DocBee-7B"
|
5 |
+
}
|
6 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"decode_strategy": "sampling",
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": [
|
6 |
+
151645,
|
7 |
+
151643
|
8 |
+
],
|
9 |
+
"pad_token_id": 151643,
|
10 |
+
"repetition_penalty": 1.05,
|
11 |
+
"temperature": 0.1,
|
12 |
+
"top_k": 1,
|
13 |
+
"top_p": 0.001
|
14 |
+
}
|
inference.yml
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
mode: paddle
|
2 |
+
Global:
|
3 |
+
model_name: PP-DocBee-7B
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model_state.pdparams
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c816b81e9e55472ba8ac45c7d8cb18c52c151f99a91cbb4f1216be7b7596802
|
3 |
+
size 16582823240
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": {"content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "unk_token": {"content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "pad_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<|object_ref_start|>", "<|object_ref_end|>", "<|box_start|>", "<|box_end|>", "<|quad_start|>", "<|quad_end|>", "<|vision_start|>", "<|vision_end|>", "<|vision_pad|>", "<|image_pad|>", "<|video_pad|>"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "unk_token": null, "bos_token": null, "eos_token": "<|im_end|>", "pad_token": "<|endoftext|>", "clean_up_tokenization_spaces": false, "split_special_tokens": false, "add_prefix_space": false, "added_tokens_decoder": {"151643": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151644": {"content": "<|im_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151645": {"content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151646": {"content": "<|object_ref_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151647": {"content": "<|object_ref_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151648": {"content": "<|box_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151649": {"content": "<|box_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151650": {"content": "<|quad_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151651": {"content": "<|quad_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151652": {"content": "<|vision_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151653": {"content": "<|vision_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151654": {"content": "<|vision_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151655": {"content": "<|image_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, "151656": {"content": "<|video_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}}, "additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<|object_ref_start|>", "<|object_ref_end|>", "<|box_start|>", "<|box_end|>", "<|quad_start|>", "<|quad_end|>", "<|vision_start|>", "<|vision_end|>", "<|vision_pad|>", "<|image_pad|>", "<|video_pad|>"], "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}", "padding_side": "left", "model_max_length": 32768, "tokenizer_class": "Qwen2Tokenizer", "added_tokens_file": null, "special_tokens_map_file": null, "chat_template_file": null}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|