Upload with huggingface_hub

.gitattributes

@@ -32,3 +32,5 @@ 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
+decoder_model_optimized.onnx.data filter=lfs diff=lfs merge=lfs -text
+decoder_with_past_model_optimized.onnx.data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "/mnt/vdb/alpaca-onnx/config.json",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

decoder_model_optimized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b485a5544a23145c81ead3c249dc53d32f0743e96050cdb28ccefca086cc94a6
+size 2441371

decoder_model_optimized.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7dd68dc6f4c26099b698d79ed0036ccf1d55541b177ad9a00ab8c453a6a13c
+size 13476831232

decoder_with_past_model_optimized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ce1b612fde067cb018b0da30d509fde9e52618b26a422a75eb328a941b2178
+size 2523515

decoder_with_past_model_optimized.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7dd68dc6f4c26099b698d79ed0036ccf1d55541b177ad9a00ab8c453a6a13c
+size 13476831232

ort_config.json

@@ -0,0 +1,33 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {
+    "disable_attention": null,
+    "disable_attention_fusion": false,
+    "disable_bias_gelu": null,
+    "disable_bias_gelu_fusion": false,
+    "disable_bias_skip_layer_norm": null,
+    "disable_bias_skip_layer_norm_fusion": false,
+    "disable_embed_layer_norm": true,
+    "disable_embed_layer_norm_fusion": true,
+    "disable_gelu": null,
+    "disable_gelu_fusion": false,
+    "disable_layer_norm": null,
+    "disable_layer_norm_fusion": false,
+    "disable_shape_inference": false,
+    "disable_skip_layer_norm": null,
+    "disable_skip_layer_norm_fusion": false,
+    "enable_gelu_approximation": false,
+    "enable_transformers_specific_optimizations": true,
+    "fp16": true,
+    "no_attention_mask": false,
+    "optimization_level": 0,
+    "optimize_for_gpu": false,
+    "optimize_with_onnxruntime_only": null,
+    "use_mask_index": false
+  },
+  "optimum_version": "1.7.4.dev0",
+  "quantization": {},
+  "transformers_version": "4.28.0.dev0",
+  "use_external_data_format": true
+}