Spaces:
Paused
Paused
Commit History
-
Fix SWE-bench service to return full problem statements
gary-boon +1: Claude- Return complete problem_statement instead of truncating at 500 chars - Enables frontend to display full multi-line issue descriptions - Fixes issue where problems were showing as one-liners 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>1d23728
-
Add SWE-bench integration and improve backend routing
gary-boon +1: Claude- Integrate SWE-bench dataset with 300 real-world GitHub issues - Add comprehensive SWE-bench evaluator UI with task selection and solution generation - Implement dynamic backend routing for CPU/GPU based on user settings - Move protected pages to (protected) folder structure for authentication - Add syntax highlighting for code displays using react-syntax-highlighter - Create confidence visualization components for transparency metrics - Fix navigation duplication issues and improve layout consistency - Add backend indicator showing which backend (Local/CPU/GPU) is being used - Implement special routing for SWE-bench to always use local backend - Add debugging and logging for backend selection - Improve error handling and user feedback 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>4444ae2
-
Consolidate HuggingFace deployment into security workflow
gary-boon +1: Claude- Update security-check.yml to deploy to both CPU and GPU spaces - Remove duplicate deploy-to-huggingface.yml workflow - Now single workflow handles security checks and dual deployment - CPU Space: visualisable-ai/api - GPU Space: visualisable-ai/api-gpu 🤖 Generated with Claude Code (https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>07be0bf -
Add GitHub Action to deploy to both CPU and GPU HuggingFace Spaces
gary-boon +1: Claude- Deploy to CPU Space (visualisable-ai/api) - Deploy to GPU Space (visualisable-ai/api-gpu) - Runs automatically on push to main branch - Provides deployment summary This ensures both spaces stay in sync with latest backend code 🤖 Generated with Claude Code (https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>8b77dd5 -
Add layer_stride parameter for PromptDiff optimization
gary-boon +1: Claude- Add layer_stride parameter to control which layers are captured - Default to 1 (all layers) for AttentionExplorer - PromptDiff can use layer_stride=2 for every other layer - Reduces matrix count from 20 to 10 for better visualization fit 🤖 Generated with Claude Code (https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>5aed1a9
-
Capture complete attention patterns after generation
gary-boon- Modified attention capture to occur after all tokens are generated - Added tokens field to TraceData model for token display - Increased sampling threshold from 20 to 100 tokens - Capture all layers instead of sampling every Nth layer - Include full token list (prompt + generated) in attention traces - This ensures complete attention matrices that match token count992dc8c
-
Update HuggingFace Space description
gary-boon +1: ClaudeAdd short_description field to correctly display what the Space does instead of the default "Generate images from text descriptions" 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>c2f6135
-
Fix: Use scaling approach instead of skipping layers
gary-boon +1: Claude- Changed strategy: scale down layer output by 99.9% instead of skipping - This maintains exact format compatibility - Avoids tuple/tensor mismatch issues entirely - Layer still runs but contributes only 0.1% to output This simpler approach should work reliably with any transformer version since we're not trying to bypass the normal data flow. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>3c774b5 -
Fix: Refine layer hook output format handling
gary-boon +1: Claude- Simplified logic to match exact output structure - Ensure compatibility with layer_norm expectations - Handle all tuple/tensor cases properly Testing different approach to prevent layer_norm type errors. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>4b03268 -
Fix: Handle single-element tuple outputs in layer hook
gary-boon +1: Claude- Fixed "tuple index out of range" when output has only one element - Properly checks tuple length before accessing output[1:] - Handles all output format cases correctly The previous fix assumed output tuples always had multiple elements, but some layers return single-element tuples. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>9e42df9
-
Fix: Correct layer hook output format for layer_norm compatibility
gary-boon +1: Claude- Fixed "layer_norm() argument 'input' must be Tensor, not tuple" error - Hook now properly handles different input/output formats - Maintains compatibility with subsequent layers expecting tensors The previous fix was returning tuples when tensors were expected, breaking layer_norm operations after skipped layers. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>070f9b8 -
Fix: Prevent hook persistence after ablation errors
gary-boon +1: Claude- Fixed tuple index error in layer hook when input format varies - Added try-finally block to ensure hooks are ALWAYS removed - Fixed indentation in generation loop - Prevents 500 errors from persisting after failed ablation The issue was that when ablation hooks failed, they weren't removed, causing ALL subsequent generation calls to fail until Space restart. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>3ee2b4b -
Fix: Downgrade transformers to 4.36.2 for PyTorch 2.1.0 compatibility
gary-boon- transformers 4.53.1 requires PyTorch 2.6+ (weights_only parameter) - Using transformers 4.36.2 which is compatible with PyTorch 2.1.0 - Still fixes the original ReDoS vulnerabilities (CVE-2025-3933, CVE-2025-5197) - Resolves HuggingFace Space startup error97df962
-
Rollback: Revert FastAPI to 0.104.1
gary-boon- FastAPI 0.109.1 caused HuggingFace Space to error (503) - WebSocket connections failing - Rolling back to stable version while investigating compatibility2b0064a -
Security Phase 1: Update FastAPI from 0.104.1 to 0.109.1
gary-boon- Fixes SNYK-PYTHON-FASTAPI-6228055 (ReDoS vulnerability) - Also updates starlette to 0.35.1 (fixes resource allocation issue) - anyio already at safe version 4.10.0 (fixes race condition) - Tested locally: All endpoints working correctly - This fixes 3 HIGH severity vulnerabilities52916a2 -
Security: Update transformers from 4.35.0 to 4.53.1
gary-boon- Fixes CVE-2025-3933 (ReDoS vulnerability) - Fixes CVE-2025-5197 (ReDoS vulnerability) - Fixes SNYK-PYTHON-TRANSFORMERS-10247398 - Fixes SNYK-PYTHON-TRANSFORMERS-11501199 - All security vulnerabilities in transformers library resolved - Tested locally and working correctlya4a41eb -
Add automated deployment to HuggingFace after security checks
gary-boon- Deploy automatically to HuggingFace Spaces after security scans pass - Only deploys on push to main branch (not on PRs) - Requires HF_TOKEN secret to be configured in GitHub repository settings33b5d17 -
Add .gitignore for Python project
gary-boon- Ignore __pycache__ and .pyc files - Ignore virtual environments - Ignore IDE files - Ignore environment and security filesb664ec4 -
Simplify workflow: Remove automated HuggingFace deployment
gary-boon- Renamed workflow to 'Security Check' since deployment is manual - Removed deploy-to-huggingface job - Keeps security scanning with Snyk, Bandit, and Safety - Manual deployment to HuggingFace continues as beforee6aff69 -
Add GitHub Actions workflow for security scanning and automated deployment
gary-boon- Implement Snyk security scanning for Python dependencies - Add Bandit for Python code security analysis - Include Safety checks for known vulnerabilities - Configure automated deployment to HuggingFace Spaces after security checks - Create comprehensive security documentation - Address known issue: transformers==4.35.0 has vulnerabilities (needs update)0e48dc7
-
feat: Add pipeline analyzer and QKV extractor for transformer visualization
gary-boon +1: ClaudeBackend Components: - TransformerPipelineAnalyzer: Captures all intermediate transformer states - Real tokenization with actual token IDs - Embedding extraction with position encodings - Attention weight extraction from QKV projections - FFN activation statistics (mean, std, sparsity, active neurons) - Output projection with top-5 predictions - Multi-token generation support with proper context updating - QKVAttentionExtractor: Specialized attention weight extraction - Supports CodeGen qkv_proj architecture - Handles GPT-2 c_attn style projections - Computes real attention scores with causal masking - Returns full attention patterns for visualization API Enhancements: - /analyze/pipeline endpoint with multi-token support - /analyze/attention endpoint for detailed attention analysis - Configurable generation parameters (temperature, top_k, top_p) - Backward compatible with single-token requests Data Integrity: - All data extracted directly from model forward pass …767a3fd
-
Add backend support for ICL emergence analysis
gary-boon +1: Claude- Implement ICL attention extractor with PyTorch hooks - Add induction head detector for pattern recognition - Create context efficiency analyzer for optimal example usage - Update model service with ICL emergence endpoints - Support real-time attention weight extraction during generation - Enable token-by-token generation for attention capture 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>920a98d
-
Add ablation support to model service with comprehensive testing
gary-boon +1: Claude- Implement ablation hooks for attention, FFN, and layer disabling - Fix string-to-int conversion for frontend compatibility - Add repetition-aware perplexity calculation - Include detailed logging for ablation debugging - Add comprehensive unit tests for ablation functionality - Fix temperature=0 handling for deterministic generation Tests confirm: - Attention ablation increases entropy from 0.44 to 1.82 - FFN ablation has strongest effect (5.32 mean difference) - All ablation patterns produce appropriately degraded outputs 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>bb8a292
-
Update backend URL to new HuggingFace organization
gary-boon- Changed from garyboon-visualisable-ai-backend.hf.space - To: visualisable-ai-api.hf.space - Updated all API routes, WebSocket URLs, and environment files - Cleaner, more professional URL structure53dcecd
-
Add CORS support for Vercel production domain
gary-boon- Allow WebSocket and API connections from visualisable-ai.vercel.app - Support all Vercel preview deployments with wildcard3c5bd74 -
Add API key authentication
gary-boon- Integrated auth.py into model_service.py endpoints - All endpoints now require X-API-Key header when API_KEY env var is set - Created setup instructions for HuggingFace Spaces configuration96a6300 -
Fix HuggingFace Spaces cache permission error
gary-boon- Set TRANSFORMERS_CACHE, HF_HOME, and HUGGINGFACE_HUB_CACHE to /tmp directories - Create cache directories with proper permissions in Dockerfile - Configure environment variables in app.py for HF Spaces - Use CPU for HF Spaces free tiera3e1f56 -
Fix backend structure - remove duplicates
gary-boon2c0fd9b -
Deploy Visualisable.ai backend with API protection
gary-boonc6c8587 -
initial commit
Verified signature0d47ef8
