Update config.json

config.json

@@ -1,38 +1,31 @@
 {
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 576,
-  "initializer_range": 0.041666666666666664,
-  "intermediate_size": 1536,
-  "is_llama_config": true,
-  "max_position_embeddings": 8192,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
-  "pad_token_id": 2,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_interleaved": false,
-  "rope_scaling": null,
-  "rope_theta": 100000,
-  "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers.js_config": {
-    "kv_cache_dtype": {
-      "fp16": "float16",
-      "q4f16": "float16"
-    }
+  "architectures": ["KimiForCausalLM"],
+  "auto_map": {
+    "AutoConfig": "configuration_kimi.KimiConfig",
+    "AutoModelForCausalLM": "modeling_kimi.KimiForCausalLM",
+    "AutoTokenizer": "tokenization_kimi.TikTokenTokenizer"
+  },
+  "bos_token": "[BOS]",
+  "eos_token": "[EOS]",
+  "hidden_size": 4096,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "model_type": "kimi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token": "[PAD]",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "linear"
   },
-  "transformers_version": "4.55.4",
+  "rope_theta": 10000.0,
+  "rms_norm_eps": 1e-06,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "TikTokenTokenizer",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "5.0.0",
   "use_cache": true,
-  "vocab_size": 49152
+  "vocab_size": 32000
 }