Update config.json

config.json

@@ -1,53 +1,69 @@
 {
-    "model": {
-        "bos_token_id": 1,
-        "context_length": 131072,
-        "decoder": {
-            "session_options": {
-                "log_id": "onnxruntime-genai",
-                "provider_options": []
-            },
-            "filename": "phi3-mini-128k-instruct-cpu-int4-rtn-block-32-acc-level-4.onnx",
-            "head_size": 96,
-            "hidden_size": 3072,
-            "inputs": {
-                "input_ids": "input_ids",
-                "attention_mask": "attention_mask",
-                "position_ids": "position_ids",
-                "past_key_names": "past_key_values.%d.key",
-                "past_value_names": "past_key_values.%d.value"
-            },
-            "outputs": {
-                "logits": "logits",
-                "present_key_names": "present.%d.key",
-                "present_value_names": "present.%d.value"
-            },
-            "num_attention_heads": 32,
-            "num_hidden_layers": 32,
-            "num_key_value_heads": 32
-        },
-        "eos_token_id": [
-            32000,
-            32007
-        ],
-        "pad_token_id": 32000,
-        "type": "phi3",
-        "vocab_size": 32064
-    },
-    "search": {
-        "diversity_penalty": 0.0,
-        "do_sample": false,
-        "early_stopping": true,
-        "length_penalty": 1.0,
-        "max_length": 131072,
-        "min_length": 0,
-        "no_repeat_ngram_size": 0,
-        "num_beams": 1,
-        "num_return_sequences": 1,
-        "past_present_share_buffer": false,
-        "repetition_penalty": 1.0,
-        "temperature": 1.0,
-        "top_k": 1,
-        "top_p": 1.0
-    }
+  "_name_or_path": "Phi-3-mini-128k-instruct",
+  "architectures": ["Phi3ForCausalLM"],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-5,
+  "rope_scaling": {
+    "long_factor": [
+      1.0299999713897705, 1.0499999523162842, 1.0499999523162842,
+      1.0799999237060547, 1.2299998998641968, 1.2299998998641968,
+      1.2999999523162842, 1.4499999284744263, 1.5999999046325684,
+      1.6499998569488525, 1.8999998569488525, 2.859999895095825,
+      3.68999981880188, 5.419999599456787, 5.489999771118164, 5.489999771118164,
+      9.09000015258789, 11.579999923706055, 15.65999984741211,
+      15.769999504089355, 15.789999961853027, 18.360000610351562,
+      21.989999771118164, 23.079999923706055, 30.009998321533203,
+      32.35000228881836, 32.590003967285156, 35.56000518798828,
+      39.95000457763672, 53.840003967285156, 56.20000457763672,
+      57.95000457763672, 59.29000473022461, 59.77000427246094,
+      59.920005798339844, 61.190006256103516, 61.96000671386719,
+      62.50000762939453, 63.3700065612793, 63.48000717163086, 63.48000717163086,
+      63.66000747680664, 63.850006103515625, 64.08000946044922, 64.760009765625,
+      64.80001068115234, 64.81001281738281, 64.81001281738281
+    ],
+    "short_factor": [
+      1.05, 1.05, 1.05, 1.1, 1.1, 1.1500000000000001, 1.2000000000000002,
+      1.2500000000000002, 1.3000000000000003, 1.3500000000000003,
+      1.5000000000000004, 2.000000000000001, 2.000000000000001,
+      2.000000000000001, 2.000000000000001, 2.000000000000001,
+      2.000000000000001, 2.000000000000001, 2.000000000000001,
+      2.000000000000001, 2.000000000000001, 2.000000000000001,
+      2.000000000000001, 2.000000000000001, 2.000000000000001,
+      2.000000000000001, 2.000000000000001, 2.000000000000001,
+      2.000000000000001, 2.000000000000001, 2.000000000000001,
+      2.000000000000001, 2.0500000000000007, 2.0500000000000007,
+      2.0500000000000007, 2.1000000000000005, 2.1000000000000005,
+      2.1000000000000005, 2.1500000000000004, 2.1500000000000004,
+      2.3499999999999996, 2.549999999999999, 2.5999999999999988,
+      2.5999999999999988, 2.7499999999999982, 2.849999999999998,
+      2.849999999999998, 2.9499999999999975
+    ],
+    "type": "su"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32064
 }