End of training

README.md

@@ -1,17 +1,20 @@
 ---
 base_model: BSC-LT/salamandra-7b
+datasets:
+- latam-gpt/es-smoltalk
 library_name: transformers
-model_name: salamandra-2B-instruct-smoltalk
+model_name: BSC-LT/salamandra-7b
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for salamandra-2B-instruct-smoltalk
+# Model Card for BSC-LT/salamandra-7b
 
-This model is a fine-tuned version of [BSC-LT/salamandra-7b](https://huggingface.co/BSC-LT/salamandra-7b).
+This model is a fine-tuned version of [BSC-LT/salamandra-7b](https://huggingface.co/BSC-LT/salamandra-7b) on the [['latam-gpt/es-smoltalk']](https://huggingface.co/datasets/['latam-gpt/es-smoltalk']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -26,6 +26,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }