Upload model

.gitattributes

@@ -33,3 +33,10 @@ 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
+phi3.5-vision-instruct-f8e4m3.uqff filter=lfs diff=lfs merge=lfs -text
+phi3.5-vision-instruct-hqq4.uqff filter=lfs diff=lfs merge=lfs -text
+phi3.5-vision-instruct-hqq8.uqff filter=lfs diff=lfs merge=lfs -text
+phi3.5-vision-instruct-q3k.uqff filter=lfs diff=lfs merge=lfs -text
+phi3.5-vision-instruct-q4k.uqff filter=lfs diff=lfs merge=lfs -text
+phi3.5-vision-instruct-q5k.uqff filter=lfs diff=lfs merge=lfs -text
+phi3.5-vision-instruct-q8_0.uqff filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,151 @@
+{
+  "_name_or_path": "Phi-3.5-vision-instruct",
+  "architectures": [
+    "Phi3VForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3_v.Phi3VConfig",
+    "AutoModelForCausalLM": "modeling_phi3_v.Phi3VForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_layer": {
+    "embedding_cls": "image",
+    "hd_transform_order": "sub_glb",
+    "projection_cls": "mlp",
+    "use_hd_transform": true,
+    "with_learnable_separator": true
+  },
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "img_processor": {
+    "image_dim_out": 1024,
+    "model_name": "openai/clip-vit-large-patch14-336",
+    "name": "clip_vision_model",
+    "num_img_tokens": 144
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3_v",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+       1.08,
+      1.1,
+      1.1300000000000001,
+      1.2800000000000002,
+      1.3100000000000003,
+      1.4500000000000004,
+      1.4500000000000004,
+      1.9500000000000008,
+      2.030000000000001,
+      2.4299999999999926,
+      2.5699999999999896,
+      2.9499999999999815,
+      3.729999999999965,
+      3.869999999999962,
+      4.189999999999955,
+      4.43999999999995,
+      4.6399999999999455,
+      4.979999999999938,
+      5.159999999999934,
+      5.279999999999932,
+      5.759999999999922,
+      5.889999999999919,
+      5.889999999999919,
+      5.969999999999917,
+      6.089999999999915,
+      6.2799999999999105,
+      6.7699999999999,
+      6.8899999999998975,
+      7.109999999999893,
+      7.129999999999892,
+      7.179999999999891,
+      7.289999999999889,
+      7.339999999999888,
+      7.559999999999883,
+      7.619999999999882,
+      7.69999999999988,
+      7.879999999999876,
+      7.879999999999876,
+      7.879999999999876,
+      7.939999999999875,
+      7.949999999999875,
+      7.979999999999874,
+      8.19999999999987,
+      8.439999999999864,
+      8.469999999999864,
+      8.589999999999861,
+      8.809999999999857,
+      8.999999999999853
+    ],
+    "type": "su"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 32064,
+  "_attn_implementation": "flash_attention_2"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32000,
+  "transformers_version": "4.38.1"
+}

phi3.5-vision-instruct-f8e4m3.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a262fecdaeadcd1f2a9eff3cd13dc07fbe8828d731a26dc44854d5caf4c2f5d3
+size 3722394666

phi3.5-vision-instruct-hqq4.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb45ff99da192c8d865f82ebef2503103580e3d06f8bc95efa1de7fd07d63de
+size 2326508586

phi3.5-vision-instruct-hqq8.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da82e937e736764282f15db3ad4559383f45856786ff36de084e1adb0ad16d33
+size 4187698314

phi3.5-vision-instruct-q3k.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a779d3c117cbbb4cdf2b731b8b2191744bab83f5bd803f135e18f5b77085af35
+size 1599473074

phi3.5-vision-instruct-q4k.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8d959d578ebf0835ce03054f37bf700d42d9a568b4c4e16072dd736fde477d
+size 2093851618

phi3.5-vision-instruct-q5k.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee2eb6bd9f344046b8a5d02517bb72842b19d68acbfe66c62b3a652ddb086f6
+size 2559149050

phi3.5-vision-instruct-q8_0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052e02d0a0f5f3c6b679c3f6ccce384ba3e7fbf9f1218d1128a38d756e209738
+size 3955041346

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "processing_phi3_v.Phi3VImageProcessor",
+    "AutoProcessor": "processing_phi3_v.Phi3VProcessor"
+  },
+  "do_convert_rgb": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Phi3VImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "num_crops": 4,
+  "num_img_tokens": 144,
+  "processor_class": "Phi3VProcessor"
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "auto_map": {
+    "AutoProcessor": "processing_phi3_v.Phi3VProcessor"
+  },
+  "processor_class": "Phi3VProcessor"
+}

residual.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f3cff11028b63d48bea7b4e5482e6fafb386b85a04ead784ac47a2ec30caba
+size 848556296

tokenizer_config.json

@@ -0,0 +1,412 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<|placeholder7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<|placeholder8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<|placeholder9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<|placeholder10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<|placeholder11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<|placeholder12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<|placeholder13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<|placeholder14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<|placeholder15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<|placeholder16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<|placeholder17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<|placeholder18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<|placeholder19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<|placeholder20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<|placeholder21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<|placeholder22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<|placeholder23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<|placeholder24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<|placeholder25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<|placeholder26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<|placeholder27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<|placeholder28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<|placeholder29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<|placeholder30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<|placeholder31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<|placeholder32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<|placeholder33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<|placeholder34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<|placeholder35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<|placeholder36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<|placeholder37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<|placeholder38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<|placeholder39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|end|>",
+    "<|user|>",
+    "<|end|>"
+  ],
+  "auto_map": {
+    "AutoProcessor": "processing_phi3_v.Phi3VProcessor"
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Phi3VProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}