Upload folder using huggingface_hub

chat_template.json

@@ -0,0 +1,3 @@
+{
+    "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 %}"
+}

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vision_config": {
+    "depth": 32,
+    "embed_dim": 1280,
+    "mlp_ratio": 4,
+    "num_heads": 16,
+    "in_chans": 3,
+    "hidden_size": 8192,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2
+  },
+  "rope_scaling": {
+    "type": "mrope",
+    "mrope_section": [
+      16,
+      24,
+      24
+    ]
+  },
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 1,
+  "top_p": 0.001,
+  "top_k": 1,
+  "transformers_version": "4.37.0"
+}

model-00001-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3289c07a0b402a877fee1622c7e4992790b630b13389e1faadb43d28a261977
+size 3890187664

model-00002-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25c1cf72100109cbe660f5b5508aae49bc90ce9ab2dabba20967d6edb1fde59
+size 3812769392

model-00003-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5994dd02d1a2f9543bbb216687f1c7341cf6efb3c18d96536836f17c149317bf
+size 3995183944

model-00004-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af985d056433efc392110c8d55f34ead92284d615b4dc3c8b7fb0787303b11f
+size 3995183944

model-00005-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcd509e4732231dc3012952276943dada5c7924698c9d1657070fa982720d07
+size 3995200440

model-00006-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65b602d77d0cf8d79e5ce60952db542b206ec61f7ca971be37863fbb95f35c3
+size 3812769400

model-00007-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50081dfba7879c900dbf7627f63d86c71f9aecff7992a5061072a3982013488b
+size 3995183968

model-00008-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fca9bbf3608c5b3b4fe1b169511c71628e1a68615f2231484ddc41b0b7022df
+size 3995183968

model-00009-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b562b5ee115567641bfff0564a70ef3a9d22520a623a1ab267f4b6ac4c893d
+size 3995200464

model-00010-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e595dfacbf9067f04765e13de404ec45f7d6e3f889d42e1eb1616ce490283b4
+size 3812769424

model-00011-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd49a8dc58a05439c9f24148b7953e908b3a304c63f60a10b7fffb21ae5cc01
+size 3995183968

model-00012-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ab38aa19e70089f2300d2ce5ba33a420e06cde9fd2924f8359f8d80808bc66
+size 3995183968

model-00013-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa174c881ca9a050f27de4ebb335e9aad863ef79d92d97e601ec96b6997de82
+size 3995200464

model-00014-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c9914644ab529e811a20f564c4e6c61d014d7bff8c71a0dd5c78cb7e2e5a55
+size 3812769424

model-00015-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d355d95439dbb9d9d8a45d4fad02e0d05d0cab74ecb5331e3f76d662e0803e67
+size 3995183968

model-00016-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e7a8eb2959a6aa4d6c2eabe8a15dbac565962456e192a1e529cd6e93175f3e
+size 3995183968

model-00017-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5672421d36d29bd7a4b4229c01d88f3df64afe740fe4949e8f766adf8d69406
+size 3995200464

model-00018-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83348a378dd07722c272bee139ddf74a28ed6c286a3ae8fc09958b6d01a7faa2
+size 3812769424

model-00019-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d970b54bbe860392d8bd558324ec9d814bacbaa4439aadee64bf3982ee9c7b69
+size 3995183968

model-00020-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9708940270dedb7ac1121aef43e532f86882194b42267ecd1b271114af0491c5
+size 3995183968

model-00021-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a006968b287e7b4df0264b325a5f96a94293cb7e28897d5dc630cc70e1003de2
+size 3995200464

model-00022-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13818d4041952cae16798a890af22bcb16f4ff2fe9521f306bf85aa62c117469
+size 3812769424

model-00023-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba4d30dbb68b3eaf26beacad4d8bf63f38c1a66909b1fea94bf99cc50d1a2ea
+size 3995183968

model-00024-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3d4f33b896eb0f8c96a3cfa7de77ccf781f4e9e430fdcbd6045f0d0a7f98f8
+size 3995183968

model-00025-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2a9eeca05b2e228fea0354ca658b11da72dfe686195e03c1e75a145207f080
+size 3995200464

model-00026-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8d71543562401806123bc7025476f0ec33e5a3b36de3a09755f9d90cd8df3f
+size 3812769424

model-00027-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26df7a6131e612d5f32d5f498cc7709568d5c72754365ae2f8c6fc55f5b1f132
+size 3995183968

model-00028-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36692c0137011babc209947df814ec91edabee6b41559ead7f07548a1103b704
+size 3995183968

model-00029-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4359a3ba1f8a6469f9564cb3e3b7f383522d6f76ba2c6f3a988d539e73d52f9
+size 3995200464

model-00030-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc538fd54f918c0930b8f125ab4c2ad3448057350a42254a2c956968988bc9af
+size 3812769424

model-00031-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773ac711c999b5507cec9972d3676f8ef42db421eaef07d92b8c395ce7084c7d
+size 3995183968

model-00032-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c80ee97446f9be21145144142313550d0bdd5be04fe9f2e1b8bc73faa94740
+size 3995183968

model-00033-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0a9a527b01c1999d42ad224ab2fc7cb17e1f24db08e7a2b471fae4412023e2
+size 3995200464

model-00034-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae83e177c0a4924cfba5674b446c2b5e2d6aac19509f5eb5cf4cb7db10cf4e7
+size 3812769424

model-00035-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f495878959e031f0269dd8648abe38692c0addd7ef77e2f3d5c74b59fb9354b5
+size 3995183968

model-00036-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0992e3fcae770470b3d5ab9eadd3fdc273d23f347b826b6f054e1c1da1ce652
+size 3995183968

model-00037-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a49e7d70bb6bc09479c9d0d205a806681b7f8bbce6dad594de14ebb6fe889a
+size 2239829584

model-00038-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d920f0d57b93710d21313e9562929bc9f39ce4eda6134232b65bf01039c6c6
+size 2491416704

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2VLProcessor"
+}

tokenizer_config.json

@@ -0,0 +1,129 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": 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|>"],
+  "bos_token": null,
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "padding_side": "left",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}