Update README.md

README.md

@@ -32,7 +32,7 @@ language:
 - es
 - en
 pipeline_tag: text-generation
-base_model: meta-llama/Meta-Llama-3-8B
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 ---
 
 
@@ -86,7 +86,7 @@ Este modelo se ha entrado usando 4xNvidia A100 80Gb y axolotl
 Esta es la configuración usada
 
 ```yaml
-base_model: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Spanish/base_model
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
 is_falcon_derived_model:
@@ -375,13 +375,13 @@ datasets:
 
 chat_template: llama3
 
-dataset_prepared_path: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Spanish/dataset
+dataset_prepared_path: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Instruct-Spanish/dataset
 
 shuffle_merged_datasets: true
 
 val_set_size: 0.005
 
-output_dir: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Spanish
+output_dir: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Instruct-Spanish
 
 adapter:
 lora_model_dir:
@@ -401,13 +401,15 @@ tokens:
   - "<reserved1>"
   - "<reserved2>"
 
+special_tokens:
+   pad_token: <|end_of_text|>
 
 neftune_noise_alpha: 5
 
 wandb_project: Mortadelo&Filemon
 wandb_entity: igarciaf
 wandb_watch:
-wandb_name: meta-llama-3-8B-spanish
+wandb_name: Meta-Llama-3-8B-Instruct-Spanish
 wandb_log_model: 
 
 gradient_accumulation_steps: 32