Upload model files

config.json

@@ -1,35 +1,35 @@
 {
   "architectures": [
-    "LlamaForCausalLM"
+    "LlamaAlbertForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "modeling_llama_albert.LlamaAlbertConfig",
+    "AutoModelForCausalLM": "modeling_llama_albert.LlamaAlbertForCausalLM",
+    "modeling_llama_albert.LlamaAlbertForCausalLM": "modeling_llama_albert.LlamaAlbertConfig"
+  },
   "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "embedding_dim": 512,
   "eos_token_id": 128001,
-  "head_dim": 64,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 16,
-  "num_key_value_heads": 8,
+  "model_type": "llama_albert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 25,
+  "num_key_value_heads": 16,
   "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,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.0.dev0",
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,9 +1,8 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "transformers_version": "4.45.0.dev0",
   "do_sample": true,
+  "eos_token_id": 128001,
   "temperature": 0.6,
-  "top_p": 0.9
+  "top_p": 0.9,
+  "transformers_version": "4.57.3"
 }