Update config.json

config.json

@@ -1,38 +1,28 @@
 {
   "architectures": [
-    "AutoModelForCausalLM"
+    "LlamaForCausalLM"
   ],
-  "model_type": "causal_lm",
-  "n_ctx": 1024,
-  "n_embd": 4096,
-  "n_head": 32,
-  "n_layer": 32,
-  "vocab_size": 32000,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "special_tokens_map_file": "special_tokens_map.json",
-  "tokenizer_config_file": "tokenizer_config.json",
-  "name_or_path": "Ozaii/W.AI-13B-Chat",
+  "model_type": "llama",
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
   "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "intermediate_size": 16384,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-5,
-  "max_position_embeddings": 2048,
-  "use_cache": false,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "pad_token_id": 1,
-  "gradient_checkpointing": true,
-  "task_type": "CAUSAL_LM",
-  "r": 64,
-  "lora_alpha": 16,
-  "lora_dropout": 0.1,
-  "bias": "none",
-  "target_modules": [
-    "q_proj",
-    "o_proj",
-    "v_proj",
-    "k_proj"
-  ]
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 128256
 }