Upload Vison CPU FP32 support

.gitattributes

@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 vision-cpu-fp16/phi-3.5-v-128k-instruct-text-embedding.onnx.data filter=lfs diff=lfs merge=lfs -text
 vision-cpu-fp16/phi-3.5-v-128k-instruct-text.onnx.data filter=lfs diff=lfs merge=lfs -text
 vision-cpu-fp16/phi-3.5-v-128k-instruct-vision.onnx.data filter=lfs diff=lfs merge=lfs -text
+vision-cpu-fp32/phi-3.5-v-128k-instruct-text-embedding.onnx.data filter=lfs diff=lfs merge=lfs -text
+vision-cpu-fp32/phi-3.5-v-128k-instruct-text.onnx.data filter=lfs diff=lfs merge=lfs -text
+vision-cpu-fp32/phi-3.5-v-128k-instruct-vision.onnx.data filter=lfs diff=lfs merge=lfs -text

vision-cpu-fp32/genai_config.json

@@ -0,0 +1,68 @@
+{
+    "model": {
+        "bos_token_id": 1,
+        "context_length": 131072,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": []
+            },
+            "filename": "phi-3.5-v-128k-instruct-text.onnx",
+            "head_size": 96,
+            "hidden_size": 3072,
+            "inputs": {
+                "inputs_embeds": "inputs_embeds",
+                "attention_mask": "attention_mask",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 32,
+            "num_hidden_layers": 32,
+            "num_key_value_heads": 32
+        },
+        "embedding": {
+            "filename": "phi-3.5-v-128k-instruct-text-embedding.onnx",
+            "inputs": {
+                "input_ids": "input_ids"
+            },
+            "outputs": {
+                "inputs_embeds": "inputs_embeds"
+            }
+        },
+        "vision": {
+            "filename": "phi-3.5-v-128k-instruct-vision.onnx",
+            "inputs": {
+                "pixel_values": "pixel_values",
+                "image_sizes": "image_sizes"
+            },
+            "outputs": {
+                "visual_features": "visual_features"
+            }
+        },
+        "eos_token_id": 32007,
+        "pad_token_id": 32000,
+        "type": "phi3v",
+        "vocab_size": 32064
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 131072,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": true,
+        "repetition_penalty": 1.0,
+        "temperature": 1.0,
+        "top_k": 1,
+        "top_p": 1.0
+    }
+}

vision-cpu-fp32/phi-3.5-v-128k-instruct-text-embedding.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81c772a0b62436c821a466819fd34b519955a2ef96bf6c76b1ed10562df785a
+size 413

vision-cpu-fp32/phi-3.5-v-128k-instruct-text-embedding.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcbf0fcb14433ac8fa82b35c39675c01fb552512b4c0e5d54e8f247046ef393
+size 394002432

vision-cpu-fp32/phi-3.5-v-128k-instruct-text.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0e9ec26fcf2f59dbdf9e7b15de3d71c8d6f17e398a887dc7a7feda96a1f986
+size 52122084

vision-cpu-fp32/phi-3.5-v-128k-instruct-text.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:214fd2e8a09b8c7b141f9095171aed6f994768a36803b7eeb9ea3be16da99dd6
+size 2327285760

vision-cpu-fp32/phi-3.5-v-128k-instruct-vision.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47793608884afaf7f78c3e4956225ecf707da36bff1cd625904d1a2393826997
+size 401995

vision-cpu-fp32/phi-3.5-v-128k-instruct-vision.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23999b06dfab2b5c81f08409167e6db85cd66e490e7dab92405fb4749a46193b
+size 444899848

vision-cpu-fp32/processor_config.json

@@ -0,0 +1,35 @@
+{
+  "processor": {
+    "name": "image_processing",
+    "transforms": [
+      {
+        "operation": {
+          "name": "decode_image",
+          "domain": "com.microsoft.extensions",
+          "type": "DecodeImage",
+          "attrs": {
+            "color_space": "BGR"
+          }
+        }
+      },
+      {
+        "operation": {
+          "name": "convert_to_rgb",
+          "domain": "com.microsoft.extensions",
+          "type": "ConvertRGB"
+        }
+      },
+      {
+        "operation": {
+          "name": "phi3_image_transform",
+          "domain": "com.microsoft.extensions",
+          "type": "Phi3ImageTransform",
+          "attrs": {
+            "num_crops": 16,
+            "num_img_tokens": 144
+          }
+        }
+      }
+    ]
+  }
+}

vision-cpu-fp32/special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|end|>",
+    "<|user|>",
+    "<|end|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

vision-cpu-fp32/tokenizer_config.json

@@ -0,0 +1,413 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+}