Add model files

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|ASSISTANT|>": 50258,
+  "<|USER|>": 50257,
+  "[PAD]": 50259
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "Locutusque/gpt2-conversational-retrain",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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,
+  "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
+    }
+  },
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 50260
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4651443807a9d7b8340381ff18cce64b8ba920d084d1845846c5eb3391c27923
+size 499285193

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c301947d63c5fa47ef9279a76ffc6d48ea6bfbf4f7f2cadf7569392c9192cfd7
+size 500808355

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d02981ad7f117a8c3042a6aa6013ac746fadd7aecfa9d30afa4a124a7c47f6f
+size 128318071

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d490d2ac81f47764e532ed46e03fffe1a5df131f144fe4c64dd0ba600619b25
+size 126559186

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25780a237345caae758997249766603017820cbc6506bba31d1eaee7f98f9dc3
+size 499291999

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1e24f98617ebdb017682175b9438d61efa29907c130c76d59176562e08b4d9
+size 126568234

quantize_config.json

@@ -0,0 +1,97 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_with_past_model": {
+            "op_types": [
+                "Constant",
+                "Shape",
+                "Softmax",
+                "Where",
+                "Transpose",
+                "Tanh",
+                "Slice",
+                "Concat",
+                "Sqrt",
+                "Add",
+                "ConstantOfShape",
+                "Reshape",
+                "Div",
+                "Cast",
+                "Squeeze",
+                "Gather",
+                "ReduceMean",
+                "Mul",
+                "Split",
+                "Range",
+                "Sub",
+                "Unsqueeze",
+                "MatMul",
+                "Gemm",
+                "Pow"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "Constant",
+                "Shape",
+                "Softmax",
+                "Where",
+                "Transpose",
+                "Tanh",
+                "Slice",
+                "Concat",
+                "Sqrt",
+                "Add",
+                "ConstantOfShape",
+                "Reshape",
+                "Div",
+                "Cast",
+                "Squeeze",
+                "Gather",
+                "ReduceMean",
+                "Mul",
+                "Split",
+                "Range",
+                "Sub",
+                "Unsqueeze",
+                "MatMul",
+                "Gemm",
+                "Pow"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Constant",
+                "Shape",
+                "Softmax",
+                "Where",
+                "Transpose",
+                "Tanh",
+                "Slice",
+                "Concat",
+                "Sqrt",
+                "Add",
+                "ConstantOfShape",
+                "Reshape",
+                "Div",
+                "Cast",
+                "If",
+                "Squeeze",
+                "Gather",
+                "ReduceMean",
+                "Mul",
+                "Split",
+                "Range",
+                "Sub",
+                "Unsqueeze",
+                "MatMul",
+                "Gemm",
+                "Pow"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<|USER|>",
+    "<|ASSISTANT|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "max_length": 256,
+  "model_max_length": 1024,
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}