Update mlc-chat-config.json

mlc-chat-config.json

@@ -1,41 +1,19 @@
 {
-  "model_type": "gpt_neox",
-  "quantization": "q4f16_1",
-  "model_config": {
-    "use_parallel_residual": false,
-    "hidden_size": 2560,
-    "intermediate_size": 10240,
-    "num_attention_heads": 32,
-    "num_hidden_layers": 32,
-    "layer_norm_eps": 1e-05,
-    "vocab_size": 50432,
-    "rotary_pct": 1.0,
-    "position_embedding_base": 10000,
-    "context_window_size": 2048,
-    "head_dim": 80,
-    "prefill_chunk_size": 2048,
-    "tensor_parallel_shards": 1,
-    "ffn_out_dtype": "float32"
-  },
-  "vocab_size": 50432,
-  "context_window_size": 2048,
-  "sliding_window_size": -1,
-  "prefill_chunk_size": 2048,
-  "attention_sink_size": -1,
-  "tensor_parallel_shards": 1,
-  "mean_gen_len": 128,
-  "max_gen_len": 512,
-  "shift_fill_factor": 0.3,
-  "temperature": 0.7,
-  "repetition_penalty": 1.0,
-  "top_p": 0.95,
-  "conv_template": "redpajama_chat",
-  "pad_token_id": 0,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
-  "tokenizer_files": [
-    "tokenizer.json",
-    "tokenizer_config.json"
-  ],
-  "version": "0.1.0"
+    "model_lib": "RedPajama-INCITE-Chat-3B-v1-q4f16_1",
+    "local_id": "RedPajama-INCITE-Chat-3B-v1-q4f16_1",
+    "conv_template": "redpajama_chat",
+    "temperature": 0.7,
+    "repetition_penalty": 1.01,
+    "top_p": 0.95,
+    "mean_gen_len": 128,
+    "max_gen_len": 512,
+    "shift_fill_factor": 0.3,
+    "estimated_vram_req": 2254857830,
+    "tokenizer_files": [
+        "tokenizer.json"
+    ],
+    "model_category": "gpt_neox",
+    "model_name": "RedPajama-INCITE-Chat-3B-v1",
+    "max_window_size": 2048,
+    "vocab_size": 50432
 }