metadata

base_model: meta-llama/Llama-3.2-1B
language:
  - en
  - hi
datasets:
  - student-abdullah/BigPharma_Generic_Q-A_Format_Augemented_Hinglish_Dataset

LoRA Adapter Layers!

Uploaded model

Developed by: student-abdullah
Finetuned from model: meta-llama/Llama-3.2-1B
Created on: 29th September, 2024
Full model: student-abdullah/Llama3.2_Medicine-Hinglish-Dataset_Fine-Tuned_29-09

Acknowledgement

Model Description

This LoRA adapter layer model is fine-tuned from the meta-llama/Llama-3.2-1B base model to specialisation related to generic medications under the PMBJP scheme. The fine-tuning process included the following hyperparameters:

Fine Tuning Template: Llama Q&A
Max Tokens: 512
LoRA Alpha: 32
LoRA Rank (r): 128
Learning rate: 1.5e-4
Gradient Accumulation Steps: 4
Batch Size: 8

Model Quantitative Performace

Training Quantitative Loss: 0.1207 (at final 800th epoch)

Limitations

This is not a fully compiled model, rather just LoRA layers