Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Constant_161_attr__value filter=lfs diff=lfs merge=lfs -text
+Constant_171_attr__value filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text

Constant_161_attr__value

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae525b5c247f1f7b8310c42b37be7aed79adadb1806bb109d1e14c8c896fc319
+size 1048576

Constant_171_attr__value

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae525b5c247f1f7b8310c42b37be7aed79adadb1806bb109d1e14c8c896fc319
+size 1048576

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "### End": 50257,
+  "### Instruction:": 50258,
+  "### Response:\n": 50259
+}

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "aisquared/dlite-v2-774m",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "custom_pipelines": {
+    "text-generation": {
+      "impl": "instruct_pipeline.InstructionTextGenerationPipeline",
+      "pt": "AutoModelForCausalLM",
+      "tf": "TFAutoModelForCausalLM"
+    }
+  },
+  "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": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 50260
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1680214930fcee9705886f8c4a96d5b06d8e7a9dcb7f95b3de5750c691dd337
+size 2649672

onnx/decoder_model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030f53b5db781ea64a146d482de7fb0a9fa283b86af870eea22a9dff443c67ed
+size 3096135680

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542e5011e4267eb5ba0ca23392243174ae09bff2bb1cc12a95f4e26ec271cc8f
+size 5288464

onnx/decoder_model_merged.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030f53b5db781ea64a146d482de7fb0a9fa283b86af870eea22a9dff443c67ed
+size 3096135680

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dccd230a9ab7f8a4987a755e89ae5a6a764f74c35083d5ddcf5f7ab4818b6706
+size 782507016

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91bd0b10d0b488d66e5de3e70100bbaac5cbbfe8cdf3e20531951f5bde7397c3
+size 779165371

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81879932dce3cbd15909fb212d73ccfc66e348800f288a30148f8480c27244f3
+size 2673105

onnx/decoder_with_past_model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030f53b5db781ea64a146d482de7fb0a9fa283b86af870eea22a9dff443c67ed
+size 3096135680

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9db025185c7581b03b10a3d3c59e90af23cc963414cd8f0bf877147e3fc579b
+size 779190321

quantize_config.json

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

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "### End",
+    "### Instruction:",
+    "### Response:\n"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}