Upload folder using huggingface_hub

config.json

@@ -1,41 +1,30 @@
 {
-  "_name_or_path": "lilmeaty/testing_semifinal",
   "architectures": [
-    "LlamaForCausalLM"
+    "PartiallySharedLayerModel"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 3072,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 24,
+  "num_attention_heads": 32,
   "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
+  "num_key_value_heads": 32,
   "pad_token_id": 128009,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.47.0",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 32000
 }