Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model_state.pdparams filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,16 @@
+{
+    "<|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

@@ -0,0 +1,6 @@
+{
+    "mode": "paddle",
+    "Global": {
+        "model_name": "PP-DocBee-2B"
+    }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "decode_strategy": "sampling",
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_k": 1,
+  "top_p": 0.001
+}

inference.yml

@@ -0,0 +1,3 @@
+mode: paddle
+Global:
+  model_name: PP-DocBee-2B

model_state.pdparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692977ef9abd3dccb7d73b8b8aeffb3ec4cdfdf0ff1bdfd2f41f76ef55262595
+size 4418043117

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+    "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

@@ -0,0 +1,146 @@
+{
+    "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
+}