Update README.md

README.md

@@ -1,18 +1,16 @@
----
-license: llama3
-datasets:
-- ai-eldorado/Brazilian_CLT_preferences
-language:
-- en
-- pt
-base_model:
-- meta-llama/Meta-Llama-3-8B-Instruct
-tags:
-- legal
----
-
-
-### ✅ **Model Card for `ai-eldorado/Brazilian_CLT_DPO`**
+---
+license: llama3
+datasets:
+- ai-eldorado/Brazilian_CLT_preferences
+language:
+- en
+- pt
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
+tags:
+- legal
+---
+
 **Model Description**  
 This model is a fine-tuned version of **LLaMA-3 8B Instruct (4-bit quantized)**, optimized using **Direct Preference Optimization (DPO)** for answering legal questions related to Brazil’s Consolidation of Labor Laws (CLT). The fine-tuning process leveraged a curated dataset of **736 human-preference triplets**, annotated by HR specialists and legal experts, to align the model with domain-specific expectations for accuracy and compliance.