Upload folder using huggingface_hub (#1)

- 78f8f0ee597e12943f71ee5523acc7282923633312c7270a3d829bef343200db (88e7f6664a82f7dda0d37a1df27255581eb48ee2)
- 3cc885f4e694ba04966a3bd7d831eb99149c413f2b83f9c5a40438ab8e12b23e (ebcce4251e78051b72b59482d04b47d684513721)
- e5390f22aea9af5c8cfd870eda3aeed3a7a26f29512c7c08fd43b97a7395427d (e82de420545b09ef64ba7948aa97e27a67243aab)
- 412f8c500316eb0ee2c963af04e2dc48abf6423649d72f757478796bb55e2ff0 (d9af8179f6eccfdf11f5aae23d6e3577b226f804)
- e92749278e4e00d0c42f2a2612bf5bde2653bf74ad715b6a19aceddf24b234f2 (5503c96f4ce54f7ee24b5606bb47b9c04aa98263)
- 895f877a9c66eb49eb30f42d6c1d7809f10095e715a5387ae387cd5d43f097ee (0d2532d39aec66b5ec608ded945d411f84a34910)
- 1a92aaa8f6403b8423dc7f8e411275d876cb6873bdf1331cb251843bc4d77775 (7bd3bf3710750b141667e706a0173d529f72f6fc)
- 6bfc412650fd3afde5a4e822a7f2df0af1db467ffaad20f2f4277d50dbba55c3 (28faad40baf584d11ae679da0784251c4c8fd111)
- a5763c57c59fe8bb00c6a01f8ab967f6de6dfe7c3cee6549c798f07e91b3c4f0 (eaae12143e0da8fe12362a924af1a026a47a626d)
- 1b8dd3588ff5a802e25cb3c0e0517d1a7b746cd9989f58b1cc232dca16eaa168 (3da061b4e60e2799da97243e3886e7f99e1d0498)
- e5f064da8e3453170a793a5aa660d86bff798bd0890b5b001f3634911cbb2172 (20923467c578c610039f0f9ad0a2f0195da26af1)
- cf11247c1a9aa4b8c43fd3a992b9dba4dffc23d2a91e0e45bd1d1c4dce6cc443 (83400e460c17ceacfcae6fa146b7e09ee02892dc)
- 5a9b7a954ddebde25599bb918b2b59b371bf76cb0a2f9ed67160cd8dfd23b488 (ec2c94e209c0260c9964fbe1626d763d992c5558)
- c2b72475fa1c9c46fd5b8ff0a76cead3bd4b113ea0974e5f579657a629bf6130 (50cac5f6e2cde5800d7fae4d80a6a681cf5de309)
- e6e8197b053eadbfc95b0c68813e19a749df76bbc1fff6b0ae0cdab4833ca835 (40f92a15ae35e4373e8171f3e27e945e77dfd690)
- 21ad6526a860fd5cf15d6009f55d00473bbe7b02a90bfd933b7e026c63861073 (1eb7a88439445a0b224b382d5cabf4e5f33d3d34)
- 5b1c1471589f9f6f89efb2771c5c12dc402df7239bd3728154e26e36b085a3b8 (9d90a5652e49385f483bbda43ed44fb1a656ae59)
- ca8ac7e232e90ff50a73a979a60ecb41adc8f730dd69c7a00ec8690e733524dc (02430696755d947c84615e9bb8fc689b917c3bd7)
- 2504514365059701cb1b6a284e9ff000b2443015393cc0cc568ba41003d7f4e2 (ee6f5e8cd5d6548d3991ef4c55195977150b51d5)
- aa06b6eaaa4698339b00f3e6df4b2214a86b7fa890b126bded9e093e71c41f4c (702ef204dfdde4db622ad06a6b396740c77223a8)
- 948c225f86a37acdd3413013a38b82fb21aaf85c9cb50d16921146c3e3dbb884 (187238cca329e2a0a8089f4411ae2bfe7daa3a3b)
- e3fe985a8a8de570d241a1fb1b4bbe6fed0776a9ead884a010b82ea12778e801 (9dd90b30d30c2d808346d626e00c6eca7e96c2e1)
- 1cc0009881171479aa0139c7e0712f98916043f8e0d8cf2dfa63006176c8e957 (b873f4b3f7a03c2c2919a032eb025a6b80287987)
- 209faf6b7e79f647aca168fc7c124e89747732578e446c5937be98c8925ccf9d (235cedb41a4d3222150be503f047e7a7b66999de)
- f8b0ff6b4d5f4072b53a7e86ef206f4c5ea3c0c3a9996855eb4521a506e643fd (565a393064d136434d68cedb006ee27e863222e6)
- cfa93b10fd711eb356ec55c9e793728b58a7ca2791bbb1c29afb9234a5a068e0 (1584dfce24be6cf69673cabe8056f264974669cb)
- 45fd1578f8e65671d7bd171a31295c9935965b855de2b09d8f1048e1d8710884 (d00e9561e7f363bed0e47f27ec948c9ce4d54c97)
- 4f99078c208fd618c26ecd180592039aa88ead92c5894bffe06b674982ea2d5e (31578d2ad4a16c92456b923c9469e558a4b65d06)
- 40eb97b87072fee12bbc34fb0fa56bf8cfd1b5016a0af163ae046cbdbbda57a0 (643844f056c7be37688df3e43ac13afbe234ccbb)
- 02021feef4f6854e2b8fa498364f69f0c363eddc1ab6cdad66f51c9c9c1b8290 (507ad173dd6c582692f609d58b13fc10ab10701e)
- bb22909f7842a00201a60cde5d50f44c8ca55e59540356bf1f5ada292643bcb6 (cb5c53d87f31e35dab24c1a6a7d024494babc3d4)
- 6b65959f1627dd310c7fb456a678eab1898ae2776f6cf33c454fa423606d9bc3 (8a4728ceed8ca96d15762d14a77ba78f0498fa15)

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<image>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,217 @@
+{
+  "_name_or_path": "lmms-lab/llava-onevision-qwen2-72b-ov",
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "ignore_index": -100,
+  "image_aspect_ratio": "anyres_max_9",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      384,
+      384
+    ],
+    [
+      384,
+      768
+    ],
+    [
+      384,
+      1152
+    ],
+    [
+      384,
+      1536
+    ],
+    [
+      384,
+      1920
+    ],
+    [
+      384,
+      2304
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      768,
+      1152
+    ],
+    [
+      768,
+      1536
+    ],
+    [
+      768,
+      1920
+    ],
+    [
+      768,
+      2304
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      1152,
+      768
+    ],
+    [
+      1152,
+      1152
+    ],
+    [
+      1152,
+      1536
+    ],
+    [
+      1152,
+      1920
+    ],
+    [
+      1152,
+      2304
+    ],
+    [
+      1536,
+      384
+    ],
+    [
+      1536,
+      768
+    ],
+    [
+      1536,
+      1152
+    ],
+    [
+      1536,
+      1536
+    ],
+    [
+      1536,
+      1920
+    ],
+    [
+      1536,
+      2304
+    ],
+    [
+      1920,
+      384
+    ],
+    [
+      1920,
+      768
+    ],
+    [
+      1920,
+      1152
+    ],
+    [
+      1920,
+      1536
+    ],
+    [
+      1920,
+      1920
+    ],
+    [
+      1920,
+      2304
+    ],
+    [
+      2304,
+      384
+    ],
+    [
+      2304,
+      768
+    ],
+    [
+      2304,
+      1152
+    ],
+    [
+      2304,
+      1536
+    ],
+    [
+      2304,
+      1920
+    ],
+    [
+      2304,
+      2304
+    ]
+  ],
+  "image_split_resolution": null,
+  "image_token_index": 151646,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "one_token",
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": 1e-06,
+  "model_type": "llava",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "projector_hidden_act": "gelu",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "text_config": {
+    "model_type": "llama"
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 32768,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vision_tower_pretrained": null,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b065da10defe076bbbf574830560ce4ff90da0a983b6596587363d9d4c77470
+size 4548815200

model-00002-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462450a3fb82f892f4435533eab9be99c3dc68c869b11a0f0b7eb4b3c075e0bc
+size 4964101384

model-00003-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde66fb3c9f640684dd9ab7ddb6570fad87deb97914c94d779f821aaa3be991d
+size 4781637328

model-00004-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be33b262d5a427eae15b54a1d1d06e4b7b1574bd1d2eb84d4d59b326ded9886
+size 4781670320

model-00005-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbf98cd7c2e65fcdd81f980d125a5e2a22f3346fe9a08019f4c35278a405489
+size 4781670360

model-00006-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe91a664edeadaa818f59ba1994edc87c7e741638839ad64c92c85e7b4531d1
+size 4964101416

model-00007-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c6a449bf2d8f3bff1b9c9957dc16fc9aabeb42985f4ae18374c36fa4d28245
+size 4781637360

model-00008-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6369b286211e4fbbc10308fdae2939e84b24cb6b8b2a9ef07ff885d7e6c98723
+size 4781670360

model-00009-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e40671d4a81735cf40111e20f37453a78b3a54ee25c413f06298a292e5bc4c
+size 4781670360

model-00010-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6eda109848b21621e68bb33b8b681921339350fc413d66d347a492db4d9993
+size 4964101416

model-00011-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3468a11d806344189f29c32c633671bea7f9deef5e8e5612e857f7589614f3
+size 4781637360

model-00012-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a111895b9a8795b4352991d900c1f88ffdaa76d3932886d724a09a290cd10d
+size 4781670360

model-00013-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c9f2426bcc26413edb4b637404c547b7c31fc9a5eaaf259c71f51c2cee363a
+size 4781670360

model-00014-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a16076b5675203d9869776b7bf2f1d76d2ac6da07626bfe75e30ea194056af1
+size 4964101416

model-00015-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6f43c1e3d866300143ea261082592cec6773dd28aa5825acbeba7795b3d679
+size 4781637360

model-00016-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197d08aadb19fc34181f04b246bda8b026509c39a8c14082b8aaf0acc2f797c4
+size 4781670360

model-00017-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad44d7c7a8c11a2b0152b637f29b320d558b886106884966db276dafce64ad34
+size 4781670360

model-00018-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77b01b954c06c753ceacf2e1a5015c66a5adbe9378f9a3fa8d24a3a16e8fa29
+size 4964101416

model-00019-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28dc64557d9a110b7b41e67d01633c633fe51f36c61977ff3a102c67d79b6437
+size 4781637360

model-00020-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a1f3fbb7f8baf3e8dd7d2f84fc2d3c000b7f7ca30000b960fd6fc19efaf7f9
+size 4781670360

model-00021-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b84d6f7515983b1a066b6f057591725a2369990cf4d1de4a4399c5b2f7ae25e
+size 4781670360

model-00022-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c9755f9b4c2e853739e5ff34a365ebf09369d41eff06d5d03531b181900260
+size 4964101416

model-00023-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d9125144fb4b949322256817529cb08e4e6201b243578cb32dc4227f676581
+size 4781637360

model-00024-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd286330f98c8ad5152e95605ba5b6241d3f0c38edc36b1186cb78e4848accb
+size 4781670360

model-00025-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb2ea7fd5c8cf4e9a4b7a9d9e323898784a8e37a7f15731773c330c660e16c4
+size 4781670360

model-00026-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142b60f1851589007af25984edd730f0b1147e83453a985275e44fad053994c2
+size 4964101416

model-00027-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a51e3cad68c3a76d4a3c53614295d871cce3d2ff2b2fead7c0d7fe85a47c73f
+size 4781637360

model-00028-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa887fb6b7a0b296daf831d519dfbb2c2104936ad85d07200c1070992136a48
+size 4781670360

model-00029-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd20a801c7ab759df52e836b1eaf7029548d9cecd9bb3ed6a3aa9598955e8e4
+size 4781670360

model-00030-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0ea3601047a2ce6a215383e3adbc0d74b5c6f0cf8c9cce6d1fe5f9bc9a9b02
+size 4157433952

model-00031-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01a2be3d0f2afe904eb8446ec11c665091864564486da582cb6e69d8a277793
+size 2491416704

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "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": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9693d87500d88307bee8bc4b6dde2691cb68f7da71c43aa13291d276fabc9a
+size 7864