Adding Evaluation Results

README.md

@@ -1,25 +1,25 @@
 ---
+language:
+- ca
+- es
+- en
 license: apache-2.0
-base_model: openlm-research/open_llama_3b_v2
-datasets:
-- xaviviro/oasst2_ca_gpt
-- xaviviro/oasst2_es_gpt
+library_name: transformers
 tags:
 - finetune
 - chatml
 - gpt4
 - catalan
-model-index:
-- name: FLAMA-0.5-3B
-  results: []
-library_name: transformers
+datasets:
+- xaviviro/oasst2_ca_gpt
+- xaviviro/oasst2_es_gpt
+base_model: openlm-research/open_llama_3b_v2
 widget:
 - text: "<|im_start|>user\n Qui va ser Isaac Newton?<|im_end|>\n<|im_start|>assistant\n"
 - text: "<|im_start|>user\n ¿Quién fue Isaac Newton?<|im_end|>\n<|im_start|>assistant\n"
-language:
-- ca
-- es
-- en
+model-index:
+- name: FLAMA-0.5-3B
+  results: []
 ---
 
 # FLAMA: Model 3B ChatML en Català i Castellà. Versió 0.5
@@ -96,4 +96,17 @@ Quien fué Isaac Newton?<|im_end|>
   journal={arXiv preprint arXiv:2302.13971},
   year={2023}
 }
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_xaviviro__FLAMA-0.5-3B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |39.23|
+|AI2 Reasoning Challenge (25-Shot)|37.97|
+|HellaSwag (10-Shot)              |67.65|
+|MMLU (5-Shot)                    |25.73|
+|TruthfulQA (0-shot)              |41.11|
+|Winogrande (5-shot)              |62.12|
+|GSM8k (5-shot)                   | 0.83|
+