SandLogicTechnologies
/

IndicPhi-mini

@@ -22,7 +22,6 @@ datasets:
 # IndicPhi-mini: Adapting Phi-mini-MoE to Indic Languages with Curated Data
 ##  Overview
 **IndicPhi-mini** is a fine-tuned version of **Microsoft’s Phi-mini-MoE**, a compact Mixture-of-Experts (MoE) model, adapted specifically for Indic languages. It is trained on a curated multilingual dataset of approximately 29 million high-quality samples, standardized into a conversational format from diverse sources. By leveraging efficient fine-tuning techniques such as **QLoRA-based quantization** and **LoRA adapters**, the model enhances Indic language capabilities while keeping resource usage practical. Evaluation on benchmark datasets shows consistent **3–4% accuracy** improvements across multiple Indic languages, demonstrating the effectiveness of targeted fine-tuning with curated data.
 a compact Mixture-of-Experts (MoE) model
@@ -107,7 +106,6 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 **Total curated dataset:** ~29 million high-quality samples
 ---
 ### Training Details
@@ -154,7 +152,6 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 Accuracy: **(Phi-mini-MoE) 21.03 → (IndicPhi-mini) 24.46 (+3.43%)**
 **MMLU-Indic**
 | Language   | Accuracy (Phi-mini-MoE) | Accuracy (Phi-mini-MoE)|
@@ -175,14 +172,14 @@ Accuracy: **(Phi-mini-MoE) 21.03 → (IndicPhi-mini) 24.46 (+3.43%)**
 Accuracy: **(Phi-mini-MoE) 27.47 → (IndicPhi-mini) 30.95 (+3.48%)**
 ## Acknowledgments
-The **Phi-mini-MoE-Instruct** models are based on the original work by **Microsoft** and Fine-tunned by **Sandlogic** development team.
 Special thanks to:
 - The [Microsoft](https://huggingface.co/microsoft) team for developing and releasing the [microsoft/Phi-mini-MoE-instruct](https://huggingface.co/microsoft/Phi-mini-MoE-instruct) model.
 ---

 # IndicPhi-mini: Adapting Phi-mini-MoE to Indic Languages with Curated Data
 ##  Overview
 **IndicPhi-mini** is a fine-tuned version of **Microsoft’s Phi-mini-MoE**, a compact Mixture-of-Experts (MoE) model, adapted specifically for Indic languages. It is trained on a curated multilingual dataset of approximately 29 million high-quality samples, standardized into a conversational format from diverse sources. By leveraging efficient fine-tuning techniques such as **QLoRA-based quantization** and **LoRA adapters**, the model enhances Indic language capabilities while keeping resource usage practical. Evaluation on benchmark datasets shows consistent **3–4% accuracy** improvements across multiple Indic languages, demonstrating the effectiveness of targeted fine-tuning with curated data.
 a compact Mixture-of-Experts (MoE) model
 **Total curated dataset:** ~29 million high-quality samples
 ---
 ### Training Details
 Accuracy: **(Phi-mini-MoE) 21.03 → (IndicPhi-mini) 24.46 (+3.43%)**
 **MMLU-Indic**
 | Language   | Accuracy (Phi-mini-MoE) | Accuracy (Phi-mini-MoE)|
 Accuracy: **(Phi-mini-MoE) 27.47 → (IndicPhi-mini) 30.95 (+3.48%)**
 ## Acknowledgments
+The **Phi-mini-MoE-Instruct** models are based on the original work by **Microsoft** and fine-tuned by the **Sandlogic** development team.
 Special thanks to:
 - The [Microsoft](https://huggingface.co/microsoft) team for developing and releasing the [microsoft/Phi-mini-MoE-instruct](https://huggingface.co/microsoft/Phi-mini-MoE-instruct) model.
+- The authors and organizations behind the **53 open-source datasets** that made this work possible.
+  The complete list of dataset sources and citations is available [here](https://github.com/sandlogic/SandLogic-Lexicons/blob/main/Images/dataset_citation.md).
 ---