Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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
+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

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 49152
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "WizardLM/WizardCoder-1B-V1.0",
+  "activation_function": "gelu_pytorch_tanh",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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,
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49153
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.33.0.dev0"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26694b5c55b14d02deb11b982e66f526e7b54873d7956445fc4c3be6ad59a04d
+size 67546220

onnx/decoder_model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6253284e87546fd7b71cd8edcc17fc9746650c1b0740d4f83b4d44a26e8a6b
+size 4548837376

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44eb9bd6f360806a76956e5c30747c7f2cb34f44ae7c588ce48f58b33c383fca
+size 135080792

onnx/decoder_model_merged.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6253284e87546fd7b71cd8edcc17fc9746650c1b0740d4f83b4d44a26e8a6b
+size 4548837376

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ae4b0a165cd7ebbd0f85d927ccf4442c7708ee40093d5d7c7860923b5537c6
+size 1274416101

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21055e3b7a8c72b60d02e746475cf1b7639c1f4b1418594190e93a2fb8a15890
+size 1206635985

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdea6acd5648a2e53c65c946ed695eb99a5956f3986f28e9e7844d9544718602
+size 67557861

onnx/decoder_with_past_model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6253284e87546fd7b71cd8edcc17fc9746650c1b0740d4f83b4d44a26e8a6b
+size 4548837376

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048d3cc8b17a2e44bb6997a541cdb02b55317ca974312999a4b83a47ded66df1
+size 1206646507

quantize_config.json

@@ -0,0 +1,100 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "Sqrt",
+                "Mul",
+                "Equal",
+                "Squeeze",
+                "And",
+                "Gather",
+                "Slice",
+                "Sub",
+                "Split",
+                "ReduceMean",
+                "Concat",
+                "Transpose",
+                "Shape",
+                "CumSum",
+                "Constant",
+                "Div",
+                "Cast",
+                "Reshape",
+                "Where",
+                "Tanh",
+                "Softmax",
+                "MatMul",
+                "ConstantOfShape",
+                "Add",
+                "Unsqueeze",
+                "Pow"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Sqrt",
+                "Mul",
+                "Equal",
+                "Squeeze",
+                "And",
+                "If",
+                "Gather",
+                "Slice",
+                "Sub",
+                "Split",
+                "ReduceMean",
+                "Concat",
+                "Transpose",
+                "Shape",
+                "CumSum",
+                "Constant",
+                "Div",
+                "Cast",
+                "Reshape",
+                "Where",
+                "Tanh",
+                "Softmax",
+                "MatMul",
+                "ConstantOfShape",
+                "Add",
+                "Unsqueeze",
+                "Pow"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_with_past_model": {
+            "op_types": [
+                "Sqrt",
+                "Mul",
+                "Squeeze",
+                "Equal",
+                "And",
+                "Gather",
+                "Slice",
+                "Sub",
+                "Split",
+                "ReduceMean",
+                "Concat",
+                "Transpose",
+                "Shape",
+                "CumSum",
+                "Constant",
+                "Div",
+                "Cast",
+                "Reshape",
+                "Where",
+                "Tanh",
+                "Softmax",
+                "MatMul",
+                "ConstantOfShape",
+                "Add",
+                "Unsqueeze",
+                "Pow"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}