Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|assistant|>": 50260,
+  "<|end|>": 50259,
+  "<|system|>": 50258,
+  "<|user|>": 50257
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "shi-zheng-qxhs/gpt2_oasst2_curated",
+  "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": 50261
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": 50256,
+  "max_new_tokens": 128,
+  "pad_token_id": 50256,
+  "penalty_alpha": 0.6,
+  "top_k": 6,
+  "transformers_version": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a48cc1a692eeff98fb5da41b9dae5e6bf53923cebc405b6a5022791877332e
+size 499288354

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3711989129bda1e163e75483108395619d30fe9e036527c4472c8ae0c7164f
+size 500811604

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1714eedeba5ce5a8383ca07d9c40ffe26c5c1741dc1128eda372307d00628f4
+size 128319015

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98139cff33249641e924b085e75f2b446aaad1a5460615b4c3eb1d5997f79a4
+size 126560042

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e732e37e26f44c1f87d934b5774ed5867bd202e15b995214e0a2de8118bc04
+size 499295159

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f29073b1b57b31d23d2836edea19e447c3b0678abf4c8f9c0043625f52bd3af6
+size 126569089

quantize_config.json

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

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50260": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|system|>",
+    "<|end|>",
+    "<|assistant|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|endoftext|><|user|>\n' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|end|><|endoftext|>\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}