Update generation_config.json

generation_config.json

@@ -1,54 +1,12 @@
 {
-    "model": {
-        "bos_token_id": 128000,
-        "context_length": 131072,
-        "decoder": {
-            "session_options": {
-                "log_id": "onnxruntime-genai",
-                "provider_options": [
-                    {
-                        "webgpu": {}
-                    }
-                ]
-            },
-            "filename": "model.onnx",
-            "head_size": 64,
-            "hidden_size": 2048,
-            "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": 16,
-            "num_key_value_heads": 8
-        },
-        "eos_token_id": 128009,
-        "pad_token_id": 128004,
-        "type": "llama",
-        "vocab_size": 128256
-    },
-    "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": true,
-        "repetition_penalty": 1.0,
-        "temperature": 1.0,
-        "top_k": 1,
-        "top_p": 1.0
-    }
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.1,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0.dev0"
 }