Add model files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 50258,
+  "<|im_start|>": 50257
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "rwl4/gpt2-medium-chat",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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": false,
+  "vocab_size": 50259
+}

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 sha256:7e06696e41469422c52f83472cdb227232ac32a24d8df10d81e712bd894359ec
+size 1421285685

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5682a841b1b7859283fe9054a664566f61ac4186ba2159b8d7a1789ba850c00f
+size 1423282329

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c60114672ff5cb77c90c80809232d5adf682aab13725d8e2f1f702601d251f
+size 360714253

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26325009f23a13338d46bbe1c06ce356acc51a2c93564730c229ce34be811c8
+size 358246823

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe60653244534093a2d5a3ca93e3fa8d008f8c7cc154f0d1b2556f1f0a6580c
+size 1421298473

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05714d4995c9170235b4bca17661b9f4d3769c0e09ac309934572b70cd11a740
+size 358263752

quantize_config.json

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

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  },
+  "pad_token": "!",
+  "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": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}