Upload config.json

config.json

@@ -1,7 +1,13 @@
 {
+  "DEFAULT_POINT_END_TOKEN": "<point_end>",
+  "DEFAULT_POINT_PATCH_TOKEN": "<point_patch>",
+  "DEFAULT_POINT_START_TOKEN": "<point_start>",
+  "_name_or_path": "outputs/LLaNA_train_stage1/LLaNA_train_stage1_realmadrid",
   "architectures": [
     "LLaNA"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -9,22 +15,23 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 2048,
+  "mm_use_point_start_end": true,
   "model_type": "llana",
+  "nf2vec_config_name": "nf2vec_2layer",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
   "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.28.1",
-  "use_cache": true,
-  "vocab_size": 32000,
   "point_backbone": "nf2vec",
   "point_backbone_ckpt": "",
-  "nf2vec_config_name": "nf2vec_2layer",
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
   "use_color": true,
-  "mm_use_point_start_end": true,
-  "DEFAULT_POINT_PATCH_TOKEN": "<point_patch>",
-  "DEFAULT_POINT_START_TOKEN": "<point_start>",
-  "DEFAULT_POINT_END_TOKEN": "<point_end>"
+  "vocab_size": 32003
 }