Add converted model and associated files

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "roneneldan/TinyStories-1M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      4
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 8,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.31.0"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f9bafb0911eac08e0835e6580a46533f6c23b288bb7d7ce7c8aee21299a333
+size 36437622

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5665be0cd6c818347fbfc14397dbe34e1fa7c7f1082466fcc957b8e7da14260
+size 45031368

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4b3266ca085eaff3130bb3c92df5955a67c92004c71c9e2c730fa55352d327
+size 24681847

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef462cb385433d47e058d99de547c7bf0f4e11e6f72f2296ba5f59f260fc5b8
+size 15964301

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396bd3f34bbf7e74a139af969b6e4d2fae003b7060c6c81ae5883c18234f9c35
+size 36443094

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27df694102e431b3ce4cfb3f051bf58d96e4e79b3c4d174125e3d6f2cb315f3f
+size 15971106

quantize_config.json

@@ -0,0 +1,88 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "decoder_with_past_model": {
+            "op_types": [
+                "Tanh",
+                "Add",
+                "Softmax",
+                "Gather",
+                "Sqrt",
+                "Sub",
+                "Unsqueeze",
+                "Range",
+                "ReduceMean",
+                "Transpose",
+                "Div",
+                "Pow",
+                "Where",
+                "Slice",
+                "Reshape",
+                "Mul",
+                "Constant",
+                "Shape",
+                "Concat",
+                "Squeeze",
+                "Cast",
+                "MatMul"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Tanh",
+                "Add",
+                "Softmax",
+                "Gather",
+                "Sqrt",
+                "Sub",
+                "Unsqueeze",
+                "Range",
+                "ReduceMean",
+                "Transpose",
+                "Div",
+                "Pow",
+                "Where",
+                "Slice",
+                "If",
+                "Reshape",
+                "Mul",
+                "Constant",
+                "Shape",
+                "Concat",
+                "Squeeze",
+                "Cast",
+                "MatMul"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "Tanh",
+                "Add",
+                "Softmax",
+                "Gather",
+                "Sqrt",
+                "Sub",
+                "Unsqueeze",
+                "Range",
+                "ReduceMean",
+                "Transpose",
+                "Div",
+                "Pow",
+                "Where",
+                "Slice",
+                "Reshape",
+                "Mul",
+                "Constant",
+                "Shape",
+                "Concat",
+                "Squeeze",
+                "Cast",
+                "MatMul"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}