Trained with Unsloth

config.json

@@ -1,6 +1,6 @@
 {
-    "model_type": "llama",
-   "architectures": [
+  "_name_or_path": "vimalnar/aware-ai-1st",
+  "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
@@ -17,13 +17,15 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128255,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.3",
+  "unsloth_version": "2024.8",
   "use_cache": true,
   "vocab_size": 128256
-}
+}

generation_config.json

@@ -8,5 +8,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.43.3"
 }