Update config.json

config.json

@@ -1,26 +1,23 @@
 {
   "architectures": [
-    "GPT2LMHeadModel"
+    "StableLmForCausalLM"
   ],
-  "model_type": "gpt2",
-  "vocab_size": 50257,
-  "n_positions": 1024,
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_layer": 12,
-  "n_head": 12,
-  "activation_function": "gelu_new",
-  "resid_pdrop": 0.1,
-  "embd_pdrop": 0.1,
-  "attn_pdrop": 0.1,
-  "layer_norm_epsilon": 1e-05,
+  "model_type": "stablelm",
+  "vocab_size": 100352,
+  "intermediate_size": 13824,
+  "hidden_size": 5120,
+  "num_hidden_layers": 40,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "hidden_act": "silu",
+  "max_position_embeddings": 4096,
+  "rope_theta": 10000.0,
+  "layer_norm_eps": 1e-05,
   "initializer_range": 0.02,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "summary_activation": null,
-  "summary_proj_to_labels": true,
-  "summary_first_dropout": 0.1,
-  "transformers_version": "4.36.0",
-  "bos_token_id": 50256,
-  "eos_token_id": 50256
+  "use_cache": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0"
 }