Spaces:
Sleeping
Sleeping
Commit History
-
Add live HuggingFace Spaces demo link to README
Adityab8a0f1b -
Add HuggingFace Space config frontmatter to README
Aditya8fec90e -
Fix README merge artifacts: remove duplicate sections and broken code blocks
Aditya3e14763 -
Merge remote changes, keep updated README
Aditya2174322 -
Revamp README with advanced layout, icons, and fixed HTML rendering
Adityae63b3ab -
Revise README for clarity and additional information
Updated README with project details, setup instructions, and benchmark results.de35d9c
-
Refactor README by removing metadata and updating content
Removed metadata section from README and updated deployment instructions.6b38c9b
-
Prepare for Hugging Face Spaces deployment
Aditya- Add HF Space YAML frontmatter to README.md (Streamlit SDK) - Update demo.py: check checkpoint-25/ (committed) instead of finetuned_model/ (gitignored) so Fine-Tuned works on HF Spaces - Update spinner message for first-run base model download868a905
-
Add Fine-Tuned benchmark results (85.3% accuracy) from checkpoint-25
Aditya- Update system3_inference.py to load LoRA adapter directly from checkpoint-25/ instead of requiring a merged finetuned_model/ dir - Add fill_r3.py: standalone script to populate r3 metrics in the existing benchmark cache without re-running API calls - Update data/benchmark_cache.json with real Fine-Tuned metrics for all 50 questions (accuracy 85.3%, ROUGE-L 0.283, HR 0.0%) - Update README benchmark table with real Fine-Tuned numbers09c4e61 -
Add LoRA checkpoint, benchmark results table, and updated README
Aditya- checkpoint-25/: LoRA fine-tune checkpoint for Qwen2.5-1.5B-Instruct (r=8, alpha=32, target q_proj+v_proj, trained on 50-topic CS Q&A data) - README: Add Benchmark Results table with real numbers from benchmark_cache.json (Baseline 81.5% acc / 1.46s, RAG 79.9% acc / 4.19s across 50 questions) - README: Updated project structure to include checkpoint-25/ and run_benchmark.py - README: Step 4 now shows how to merge LoRA adapter into finetuned_model/268a4fa -
Major upgrade: 50-question benchmark, persistent analytics, paper-style TABLE II
Adityademo.py changes: - BENCHMARK_QUESTIONS now dynamically loads all 50 keys from reference_answers.json instead of a hardcoded 6-item list - Quick Questions grid fixed: 3-column layout (i % 3) prevents button overflow - compute_auto_metrics() extended with answer_relevance and faithfulness metrics - _estimate_cost() helper added for per-query USD cost estimation - run_benchmark() stores 7 metric groups per row (rouge, sim/accuracy, groundedness, answer_relevance, faithfulness, cost, latency) - benchmark_kpis() computes all 8 TABLE II metrics including hallucination rate and weighted overall score (1–5) - Analytics always visible: zero-KPI fallback renders charts and table even before first benchmark run; empty-state annotation shown on Plotly charts - Benchmark persistence: results saved to data/benchmark_cache.json after run and loaded from cache on every app startup — run once, display permanently - Analytics table expanded to TABLE II format with Best and Unit columns data/r…900c573
-
Update README with auto-metrics docs and fix card rendering bugs
AdityaREADME changes: - Updated "What It Does" to describe automatic metric chips, winner/hallucination badges, and the Auto-Benchmark runner instead of manual rating system - Added "Auto-Evaluation Metrics" section documenting Accuracy, ROUGE-L, Groundedness, Context Relevance, Latency, Win count, and Low Confidence - Resolved merge conflict by keeping project README (not model card template) demo.py changes: - Add safe_answer() helper: html.escape() + \n -> <br> to prevent Streamlit's markdown parser from exiting the HTML block on blank lines in LLM answers - Fix _header_badge() returning "" (empty string) causing a whitespace-only line that terminated the HTML block, rendering card HTML as literal text — now returns <span></span> as a safe non-empty placeholder - Fix run_benchmark() using wrong key 'sem_sim' instead of 'accuracy', causing all benchmark accuracy/win scores to show as 0% - Remove stale rating_submitted session state reference2b2f4cc
-
Fix card rendering: safe_answer(), benchmark accuracy key, and badge blank-line bug
Aditya- Replace html_lib.escape() with safe_answer() which also converts \n to <br>, preventing Streamlit's markdown parser from exiting the HTML block mid-card - Fix _header_badge() returning "" (empty string) causing a whitespace-only line that terminated the HTML block — now returns <span></span> as a safe placeholder - Fix run_benchmark() using wrong key 'sem_sim' instead of 'accuracy', causing all benchmark accuracy scores to show as 0% - Install rouge-score package for ROUGE-L metric computation - Remove stale rating_submitted session state reference2215d95
-
Update README to remove metadata
Removed metadata section from README.9d8b973 -
Major upgrade: auto-metrics, Plotly charts, Qwen2.5, PDF support, expanded KB
Aditya- Add ROUGE-L and semantic similarity auto-metrics per answer card - Add Plotly bar charts for aggregate quality/speed comparison in Analytics section - Upgrade fine-tuned model from TinyLlama to Qwen/Qwen2.5-1.5B-Instruct - Update Colab notebook with Qwen2.5 model and ChatML prompt format - Add PDF ingestion to RAG pipeline (drop PDFs into data/pdfs/) - Add 5 new knowledge base docs: big_o_notation, heaps, sql_basics, typescript_basics, git_basics - Add data/reference_answers.json with 21 Q&A pairs for automated scoring - Add HuggingFace Spaces frontmatter and deploy guide to README - Add plotly, rouge-score, pypdf, langchain-huggingface, numpy to requirementsa52cc98
-
Add project README with architecture, tech stack, and setup guide
Adityafc72b2a -
Add LLM vs RAG vs Fine-Tuning comparison project
Aditya4a3f117