🚀 Subida del modelo fusionado con LoRA (HTTP)

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -33,7 +34,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.2",
+  "transformers_version": "4.48.3",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -8,5 +8,5 @@
   ],
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.50.2"
+  "transformers_version": "4.48.3"
 }

tokenizer_config.json

@@ -2059,5 +2059,5 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "tokenizer_class": "PreTrainedTokenizer"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }