MohamedAhmedAE
/

Llama-3.2-3B-Instruct-Medical-Finetune-v4

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

MohamedAhmedAE commited on about 8 hours ago

Commit

eb43460

·

verified ·

1 Parent(s): ebab132

Update config.json

Files changed (1) hide show

config.json +4 -4

config.json CHANGED Viewed

@@ -10,16 +10,16 @@
     128008,
     128009
   ],
-  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 16,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

     128008,
     128009
   ],
+  "head_dim": 128,
   "hidden_act": "silu",
+  "hidden_size": 3072,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,