Update config.json

config.json

@@ -1,52 +1,39 @@
 {
-  "_name_or_path": "huihui-ai/Llama-3.2-3B-Instruct-abliterated",
-  "model_type": "llama",
-  "torch_dtype": "float16",
-  "transformers_version": "4.46.3",
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "vocab_size": 128256,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": [
     128001,
     128008,
     128009
   ],
-  "pad_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
   "hidden_size": 3072,
+  "initializer_range": 0.02,
   "intermediate_size": 8192,
-  "num_hidden_layers": 28,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
   "num_attention_heads": 24,
+  "num_hidden_layers": 28,
   "num_key_value_heads": 8,
-  "head_dim": 128,
-  "max_position_embeddings": 131072,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": {
-    "type": "linear",
-    "factor": 32
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
   },
-  "rope_theta": 500000,
-  "hidden_act": "silu",
-  "initializer_range": 0.02,
-  "rms_norm_eps": 0.00001,
-  "layer_norm_eps": 0.00001,
-  "attention_bias": false,
-  "mlp_bias": false,
-  "pretraining_tp": 1,
+  "rope_theta": 500000.0,
   "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
   "use_cache": true,
-  "shared_input_output_embedding": true,
-  "attention_dropout": 0,
-  "hidden_dropout_prob": 0.1,
-  "attn_dropout_prob": 0.1,
-  "residual_dropout_prob": 0,
-  "ffn_dropout_prob": 0.1,
-  "output_projection": true,
-  "position_embedding_type": "rotary",
-  "use_rope": true,
-  "gradient_checkpointing": false,
-  "multi_query_attention": false,
-  "output_attentions": false,
-  "output_hidden_states": false,
-  "layerdrop": 0
+  "vocab_size": 128256
 }