Update config.json

config.json

@@ -1,20 +1,24 @@
 {
-  "_name_or_path": "SaiKamalKadarla/dragon-mistral-7b-v0-RyobiIntent-epoch2",
+  "_name_or_path": "SaiKamalKadarla/gemma-2b-it-RyobiIntent-2000steps",
   "architectures": [
-    "MistralForCausalLM"
+    "GemmaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -31,12 +35,11 @@
     "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 256000
 }