Upload 32 files

config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "decoder_start_token_id": 50256,
+    "embd_pdrop": 0.1,
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "layer_norm_epsilon": 1e-05,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "pad_token_id": 50256,
+    "reorder_and_upcast_attn": false,
+    "resid_pdrop": 0.1,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "encoder_stride": 16,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-12,
+    "model_type": "vit",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "pooler_act": "tanh",
+    "pooler_output_size": 768,
+    "qkv_bias": true,
+    "torch_dtype": "float32"
+  },
+  "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": "4.52.4",
+  "use_cache": true
+}

decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f803a48d8de73a0b0940a0152881fec87a3115f9d2f33c96eaed7ddabe918010
+size 611915715

decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95eb4d9d637eb749f2fca9a25cdcfcd1f3531627e635085485d3fd28cb3826b9
+size 613001536

decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4836b87c7fee88c400892799b4a1bd71fb7debdc5c9f9e8821f477c1bc7f53
+size 611660787

encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fcf7f4a3d5c1b0134b3e9c104b9e687545d1df634eeeb1d99acc0ee15566a6
+size 343383419

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "decoder_start_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

onnx/decoder_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c43dd9e55611c474463bb1f86e4050aab07651a5908ff338be67c7892cf3b72
+size 611915734

onnx/decoder_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ca72a6274ee629bef64de8ccec8a9655a51865c82be18aef117e12d02c6ee7
+size 306309630

onnx/decoder_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1bdf3484511ef4421be40467fae696762e644248761cdd57d73ecddc2611c40
+size 308564516

onnx/decoder_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c43dd9e55611c474463bb1f86e4050aab07651a5908ff338be67c7892cf3b72
+size 611915734

onnx/decoder_model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304e2fdad1bea86c1fe2e0eab72b1090c810f7b57da435ead9c28987f1b78ca3
+size 306309649

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1bdf3484511ef4421be40467fae696762e644248761cdd57d73ecddc2611c40
+size 308564516

onnx/decoder_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2d3cd525c9ebc3b3689a9b2a2d8e01a2fe5d940c8862e2f24a09d12aabfcbc
+size 308564562

onnx/decoder_with_past_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdca4b52161e0f4e6eda11beb4bcbfc039a4dba3cd27a4a2e0e1dbe847be48f6
+size 611660806

onnx/decoder_with_past_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f597e7e7964d2900389aa050964d6846f0aede63bf59e0a01f6c871adcb6b38
+size 306059317

onnx/decoder_with_past_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d207ebd90ad544a2451eb4ca2cda59f2e4163f359b8969fb4db0fe605013a5
+size 308307860

onnx/decoder_with_past_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdca4b52161e0f4e6eda11beb4bcbfc039a4dba3cd27a4a2e0e1dbe847be48f6
+size 611660806

onnx/decoder_with_past_model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0f56003cb2e404bdbd3685f8983ceb9c5b216d5a3eb31785ef87a074e446f9
+size 306059336

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d207ebd90ad544a2451eb4ca2cda59f2e4163f359b8969fb4db0fe605013a5
+size 308307860

onnx/decoder_with_past_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e71b394820f981a9154acbd31d202f2a45c290f91c4138116e2ba2691e44e12
+size 308307906

onnx/encoder_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667a98bc70c8020e59b7ae4853207d55b0475d6568a89f3a242011842b0506b4
+size 51431741

onnx/encoder_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370e573eec80ab59b72999d7c525f648f0db0400d4d635f8f814bd46e255979f
+size 171786205

onnx/encoder_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597463e3fdcf779bb7979464eb9d011751c524ab0ecc6c1af9acb45a31284612
+size 86899824

onnx/encoder_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8edf694ef56774d6d669d67bbf2cb53dbb0f90ac8cdb81a8df5dff32b46d505d
+size 56739629

onnx/encoder_model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f05b7bd9c809f59d6ef0d4077c6d17fa468be0c0b875924de77b2eb9c75163
+size 49703408

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58c417d80464a2a787d96d59a0c0af6aa0220c4d4fbff82917925c1e577b818
+size 86899861

onnx/encoder_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58c417d80464a2a787d96d59a0c0af6aa0220c4d4fbff82917925c1e577b818
+size 86899861

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "max_length": 32,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}