Upload 16 files

config.json

@@ -1,184 +1,183 @@
-{
-  "_name_or_path": "mozilla/distilvit",
-  "architectures": [
-    "VisionEncoderDecoderModel"
-  ],
-  "decoder": {
-    "_name_or_path": "distilbert/distilgpt2",
-    "_num_labels": 1,
-    "activation_function": "gelu_new",
-    "add_cross_attention": true,
-    "architectures": [
-      "GPT2LMHeadModel"
-    ],
-    "attn_pdrop": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 50256,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "embd_pdrop": 0.1,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 50256,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "id2label": {
-      "0": "LABEL_0"
-    },
-    "initializer_range": 0.02,
-    "is_decoder": true,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0
-    },
-    "layer_norm_epsilon": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "gpt2",
-    "n_ctx": 1024,
-    "n_embd": 768,
-    "n_head": 12,
-    "n_inner": null,
-    "n_layer": 6,
-    "n_positions": 1024,
-    "no_repeat_ngram_size": 0,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "reorder_and_upcast_attn": false,
-    "repetition_penalty": 1.0,
-    "resid_pdrop": 0.1,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "scale_attn_by_inverse_layer_idx": false,
-    "scale_attn_weights": true,
-    "sep_token_id": null,
-    "summary_activation": null,
-    "summary_first_dropout": 0.1,
-    "summary_proj_to_labels": true,
-    "summary_type": "cls_index",
-    "summary_use_proj": true,
-    "suppress_tokens": null,
-    "task_specific_params": {
-      "text-generation": {
-        "do_sample": true,
-        "max_length": 50
-      }
-    },
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 50257
-  },
-  "decoder_start_token_id": 50256,
-  "encoder": {
-    "_name_or_path": "google/vit-base-patch16-224-in21k",
-    "add_cross_attention": false,
-    "architectures": [
-      "ViTModel"
-    ],
-    "attention_probs_dropout_prob": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "encoder_stride": 16,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.0,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 224,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-12,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "vit",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 16,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "qkv_bias": true,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  },
-  "eos_token_id": 50256,
-  "is_encoder_decoder": true,
-  "model_type": "vision-encoder-decoder",
-  "pad_token_id": 50256,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.40.2"
-}
+{
+  "_name_or_path": "mozilla/distilvit",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "distilbert/distilgpt2",
+    "_num_labels": 1,
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 6,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "google/vit-base-patch16-224-in21k",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 16,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 50256,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 50256,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.33.2"
+}

generation_config.json

@@ -1,5 +1,5 @@
-{
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
-  "transformers_version": "4.40.2"
-}
+{
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7025996166a391f1a16c5087f33e58b13742635f068dcfba863f481229d3aa9
-size 385863272
+oid sha256:7351a7eaeeec455e70e68007a1dcf7307e245473f53da6b13312016ad5d992d3
+size 385864797

onnx/decoder_model_merged.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67601b107ac8e081023020798926374cc1891e9b20888049b25af8b26e525036
-size 387339536
+oid sha256:f951eec84e5b043b03ac6a94556e7b0f16846282bc577adec061c848119aadac
+size 387342586

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc5f9d3406b3311eea01659346b322c08c2ca993d6c4c9a5efef56894b0cb83e
-size 99755449
+oid sha256:1ff8ee2b032955fd71b217c61751a92a6386e7b0e31228ef806a89a923bca34d
+size 99759578

onnx/decoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365eb53fde6f242e34beec14cb7b1eeb9c80538fa1527cbe3104fcbaa5bde638
-size 98063697
+oid sha256:737759dec1b90e1e29eb61e271951db84e3e677d6f8332db64bd4a15fe931711
+size 98065762

onnx/decoder_with_past_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b578768f4e7f43a54c96353cd8b06aed97c8d94411522906f021ca9195132b
-size 385862852
+oid sha256:b99196af93603df1ef7eeb9676177d99c0a4a11b01e266ae5cb9327abe968c54
+size 385864377

onnx/decoder_with_past_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89bab295c36f14f4dae4d6f3440f06c8620ca3b3aa671fa9e9c7114637eaa297
-size 98061104
+oid sha256:12e5aad5d80e36cd4f9b2d45297732b01fd9e6503e6393aa393b4c13533c53e7
+size 98063169

onnx/encoder_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef6f2aa561891b1d39b2e79411e63cf7859ba2fa5a1a56376a13f7571c8f87a
-size 343440610
+oid sha256:aacd44f8cc26c1a0539f5db1fcb98cf3baad2c5e62583b913ed501daf1419e96
+size 343440632

onnx/encoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7ae423fd73637b434c8a3266ea049c25b09e321cef8d0c97138ba16ab01fda
-size 87038151
+oid sha256:13062fd1801c38f1039ed439e792b9e08dc8eb0b006d4dd64146575e641c4286
+size 87038173

quantize_config.json

@@ -4,120 +4,120 @@
     "per_model_config": {
         "decoder_with_past_model": {
             "op_types": [
-                "Constant",
                 "Sqrt",
-                "Reshape",
-                "Concat",
-                "Cast",
                 "Split",
-                "Transpose",
+                "Unsqueeze",
+                "Tanh",
+                "Gemm",
+                "MatMul",
+                "Cast",
+                "Div",
+                "Pow",
                 "Add",
-                "Slice",
+                "Constant",
+                "Reshape",
+                "ConstantOfShape",
                 "Range",
+                "Slice",
+                "Where",
+                "Concat",
                 "Shape",
                 "Squeeze",
-                "Div",
-                "ConstantOfShape",
-                "Gather",
-                "Pow",
-                "MatMul",
-                "Gemm",
+                "ReduceMean",
                 "Softmax",
-                "Where",
-                "Unsqueeze",
+                "Gather",
+                "Sub",
                 "Mul",
-                "ReduceMean",
-                "Tanh",
-                "Sub"
+                "Transpose"
             ],
             "weight_type": "QInt8"
         },
         "decoder_model": {
             "op_types": [
-                "Constant",
                 "Sqrt",
-                "Reshape",
-                "Concat",
-                "Cast",
                 "Split",
-                "Transpose",
+                "Unsqueeze",
+                "Tanh",
+                "Gemm",
+                "MatMul",
+                "Cast",
+                "Div",
+                "Pow",
                 "Add",
-                "Slice",
+                "Constant",
+                "Reshape",
+                "ConstantOfShape",
                 "Range",
+                "Slice",
+                "Where",
+                "Concat",
                 "Shape",
                 "Squeeze",
-                "Div",
-                "ConstantOfShape",
-                "Gather",
-                "Pow",
-                "MatMul",
-                "Gemm",
+                "ReduceMean",
                 "Softmax",
-                "Where",
-                "Unsqueeze",
+                "Gather",
+                "Sub",
                 "Mul",
-                "ReduceMean",
-                "Tanh",
-                "Sub"
+                "Transpose"
             ],
             "weight_type": "QInt8"
         },
         "encoder_model": {
             "op_types": [
-                "Constant",
                 "Sqrt",
-                "Reshape",
-                "Erf",
-                "Concat",
-                "Transpose",
-                "Add",
-                "Slice",
+                "Unsqueeze",
                 "Equal",
-                "Shape",
+                "MatMul",
                 "Div",
-                "ConstantOfShape",
-                "Gather",
                 "Pow",
-                "MatMul",
+                "Add",
+                "Erf",
+                "Constant",
+                "Reshape",
+                "ConstantOfShape",
+                "Slice",
+                "Where",
                 "Conv",
+                "Concat",
+                "Shape",
+                "ReduceMean",
                 "Softmax",
-                "Where",
-                "Unsqueeze",
+                "Gather",
                 "Expand",
                 "Mul",
-                "ReduceMean",
-                "Sub"
+                "Sub",
+                "Transpose"
             ],
             "weight_type": "QUInt8"
         },
         "decoder_model_merged": {
             "op_types": [
-                "Constant",
                 "Sqrt",
-                "Reshape",
-                "Concat",
-                "Cast",
                 "Split",
-                "Transpose",
+                "If",
+                "Unsqueeze",
+                "Tanh",
+                "Gemm",
+                "MatMul",
+                "Cast",
+                "Div",
+                "Pow",
                 "Add",
-                "Slice",
+                "Constant",
+                "Reshape",
+                "ConstantOfShape",
                 "Range",
+                "Slice",
+                "Where",
+                "Concat",
                 "Shape",
                 "Squeeze",
-                "Div",
-                "ConstantOfShape",
-                "Gather",
-                "Pow",
-                "MatMul",
-                "If",
-                "Gemm",
+                "ReduceMean",
                 "Softmax",
-                "Where",
-                "Unsqueeze",
+                "Gather",
+                "Sub",
                 "Mul",
-                "ReduceMean",
-                "Tanh",
-                "Sub"
+                "Transpose"
             ],
             "weight_type": "QInt8"
         }