https://github.com/gitgoap/sarvam-fellow
https://github.com/gitgoap/sarvam-fellow
Last synced: 11 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/gitgoap/sarvam-fellow
- Owner: gitgoap
- Created: 2025-03-16T18:08:59.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-24T17:20:51.000Z (about 1 year ago)
- Last Synced: 2025-06-22T08:05:47.191Z (about 1 year ago)
- Language: Jupyter Notebook
- Size: 1.79 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Sarvam-Fellow Assignment
### **1. baseline-inference**
- Contains code for inference using `meta-llama/Llama-3.2-11B-Vision`.
- Works on the given [dataset](https://drive.google.com/drive/folders/1nQeKL48BTjodz7JfvVWj5kFMfdc1U4G-).
### **2. finetuning**
- Details for fine-tuning `meta-llama/Llama-3.2-11B-Vision`.
### **3. dataset-ground-truth**
- Code for generating the ground truth CSV file.
- Includes code for ground truth generation.
Processed dataset pushed to [Hugging Face](https://huggingface.co/datasets/MLap/ScannedBookPages)
### **4. Text Organization**
- Includes code to structure text extracted from images using Mistral API
### Summary
Baseline Inference Metric
- Average Sequence Accuracy: 0.330054
- WER (Average): 2.532779
- CER (Average): 1.510348
FineTuned Inference Metric
- Average Sequence Accuracy: 0.448970
- WER (Average): 1.685408
- CER (Average): 1.428369