Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./models/TheBloke/Llama-2-7b-chat-fp16-w8-g128",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e70270bfcc9239918ab41968230e6c96b228c6c8d1fdb0bdb09881631eadf4a
-size 332371926
+oid sha256:b8e5997534698ab4dcebafbc8267016e17e6ce336592dba2d82cd8be61bd50d7
+size 330767818

onnx/decoder_model_merged_quantized.onnx_data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6752bb9b7e955f3098598555e3716f5da689ae2ee8c416b85b37ef873dddbc6
+oid sha256:1166a5e8849121216988329ee41544c2e6c31d3c9e570f44825c8974ecd04ddb
 size 6739214336

onnx/quantize_config.json

@@ -5,35 +5,35 @@
     "per_model_config": {
         "decoder_model_merged": {
             "op_types": [
+                "Where",
+                "Softmax",
+                "Pow",
                 "Div",
-                "Less",
-                "Cast",
-                "Add",
-                "Unsqueeze",
-                "Reshape",
-                "Shape",
-                "Range",
+                "If",
                 "Concat",
-                "Where",
-                "Identity",
-                "MatMul",
                 "Equal",
-                "Softmax",
-                "ConstantOfShape",
-                "Neg",
-                "Slice",
+                "Cast",
                 "Sqrt",
-                "Expand",
-                "Sigmoid",
                 "Transpose",
                 "ReduceMean",
-                "Mul",
+                "Range",
                 "Squeeze",
                 "Sub",
-                "Pow",
+                "Identity",
+                "Shape",
+                "MatMul",
+                "Unsqueeze",
+                "Sigmoid",
                 "Gather",
-                "If",
-                "Constant"
+                "ConstantOfShape",
+                "Expand",
+                "Add",
+                "Neg",
+                "Constant",
+                "Mul",
+                "Reshape",
+                "Less",
+                "Slice"
             ],
             "weight_type": "QInt8"
         }