Update config.json

config.json

@@ -1,24 +1,28 @@
 {
-  "alibi": false,
-  "apply_residual_connection_post_layernorm": false,
+  "_name_or_path": "/raid/younes/gg-converted-ckpt/gemma-7b-it",
   "architectures": [
-    "falcon-7b-sharded-bf16-finetuned-mental-health-conversational"
+    "GemmaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bias": false,
-  "bos_token_id": 11,
-  "eos_token_id": 11,
-  "hidden_dropout": 0.0,
-  "hidden_size": 4544,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "falcon",
-  "multi_query": true,
-  "n_head": 71,
-  "n_layer": 32,
-  "parallel_attn": true,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.30.0.dev0",
+  "transformers_version": "4.38.0.dev0",
   "use_cache": true,
-  "vocab_size": 65024
+  "vocab_size": 256000
 }