Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/vision_encoder.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,248 +1,32 @@
 {
-  "_commit_hash": "239af0aa4662d7fdac1fc5efe21f8f0cb0c35105",
   "_name_or_path": "facebook/sam-vit-huge",
   "architectures": [
     "SamModel"
   ],
   "initializer_range": 0.02,
   "mask_decoder_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_downsample_rate": 2,
-    "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,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "relu",
-    "hidden_size": 256,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "iou_head_depth": 3,
-    "iou_head_hidden_dim": 256,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "mlp_dim": 2048,
-    "model_type": "",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 2,
-    "num_multimask_outputs": 3,
-    "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,
-    "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,
-    "transformers_version": "4.29.2",
-    "typical_p": 1.0,
-    "use_bfloat16": false
+    "model_type": ""
   },
   "model_type": "sam",
   "prompt_encoder_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "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,
-    "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_size": 256,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_embedding_size": 64,
-    "image_size": 1024,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "mask_input_channels": 16,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "",
-    "no_repeat_ngram_size": 0,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_point_embeddings": 4,
-    "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": {},
-    "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,
-    "transformers_version": "4.29.2",
-    "typical_p": 1.0,
-    "use_bfloat16": false
+    "model_type": ""
   },
-  "transformers_version": null,
+  "transformers_version": "4.33.0.dev0",
   "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 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,
     "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "global_attn_indexes": [
       7,
       15,
       23,
       31
     ],
-    "hidden_act": "gelu",
     "hidden_size": 1280,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 1024,
     "initializer_factor": 1.0,
-    "initializer_range": 1e-10,
     "intermediate_size": 6144,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
     "mlp_dim": 5120,
-    "mlp_ratio": 4.0,
     "model_type": "",
-    "no_repeat_ngram_size": 0,
     "num_attention_heads": 16,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
     "num_hidden_layers": 32,
-    "num_pos_feats": 128,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_channels": 256,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 16,
-    "prefix": null,
-    "problem_type": null,
-    "projection_dim": 512,
-    "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,
-    "transformers_version": "4.29.2",
-    "typical_p": 1.0,
-    "use_abs_pos": true,
-    "use_bfloat16": false,
-    "use_rel_pos": true,
-    "window_size": 14
+    "projection_dim": 512
   }
 }

onnx/prompt_encoder_mask_decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bf9ed56968e0e4070629ba4190a715be9b09fe6e7c6afcf7ed70703cded437
+size 16557844

onnx/prompt_encoder_mask_decoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e229d24889ff0550f67e95b8ce68dec42492a6c25eacb9e47b1c2e4d3f37ff94
+size 4903718

onnx/vision_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f29ddfa848550eb784ce3fb4164588a27328e28c5e697f975ab92a3be27cfc8e
+size 2001683

onnx/vision_encoder.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e452133f5d9dec76ba7d518a3690e5989e13f894ab07d561c38180a692ab353a
+size 2548105216

onnx/vision_encoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c84d6fce9338c8ca204224e4a2354150fb3be2b5d121a463207d2103a02c46bd
+size 659577872

quantize_config.json

@@ -0,0 +1,82 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "prompt_encoder_mask_decoder": {
+            "op_types": [
+                "Reshape",
+                "Concat",
+                "OneHot",
+                "ReduceMean",
+                "Gather",
+                "Sin",
+                "Div",
+                "Add",
+                "Slice",
+                "ScatterND",
+                "ConstantOfShape",
+                "Where",
+                "Expand",
+                "Constant",
+                "Sqrt",
+                "Mul",
+                "Sub",
+                "Not",
+                "Cos",
+                "Range",
+                "MatMul",
+                "Equal",
+                "Tile",
+                "Erf",
+                "Shape",
+                "Softmax",
+                "Neg",
+                "Unsqueeze",
+                "Transpose",
+                "ConvTranspose",
+                "Pow",
+                "Relu",
+                "Cast"
+            ],
+            "weight_type": "QInt8"
+        },
+        "vision_encoder": {
+            "op_types": [
+                "Reshape",
+                "Concat",
+                "ReduceMean",
+                "Gather",
+                "Sin",
+                "Div",
+                "Add",
+                "Slice",
+                "Pad",
+                "Resize",
+                "Conv",
+                "ConstantOfShape",
+                "Identity",
+                "Expand",
+                "Constant",
+                "Sqrt",
+                "Mul",
+                "Squeeze",
+                "Sub",
+                "Cos",
+                "MatMul",
+                "Range",
+                "Tile",
+                "Erf",
+                "Shape",
+                "Softmax",
+                "Einsum",
+                "Unsqueeze",
+                "Split",
+                "Transpose",
+                "Mod",
+                "Pow",
+                "Cast"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}