shoo-Hermes#10
Open
morongosteve wants to merge 13 commits into
Open
Conversation
This commit adds complete support for running the Xortron2025-24B GGUF model locally using llama.cpp, providing a free alternative to paid API services. Features: - Local inference with Xortron2025 (darkc0de/Xortron2025 on HuggingFace) - Setup scripts for llama.cpp build and model download - Python wrapper (xortron_inference.py) with OpenAI-compatible API - post_maker_local.py with dual-mode support (API/local inference) - Comprehensive documentation and examples - .gitignore to exclude large model files and build artifacts Benefits: - Free inference (no API costs) - 100% private (runs completely locally) - Full control over model parameters - Works offline once set up Model specs: - Size: 24B parameters (~19.3 GB download) - Quantization: Q6_K (6-bit GGUF) - Architecture: Mistral/Llama-family - RAM required: 21GB+ - License: WTFPL Files added: - agent/local_inference/setup_llama_cpp.sh - agent/local_inference/download_xortron.sh - agent/local_inference/xortron_inference.py - agent/local_inference/example_usage.py - agent/local_inference/README.md - agent/engines/post_maker_local.py - .gitignore Documentation: See agent/local_inference/README.md for setup instructions and usage examples.
…e-01DuJn8CQc1gKTi9HNviJS3g
This commit significantly expands the Xortron2025 local inference setup with: **New Features:** - Windows support via PowerShell scripts (setup_llama_cpp.ps1, download_xortron.ps1) - Git-LFS alternative download method (download_xortron_lfs.sh) - Comprehensive verification script (verify_setup.py) that checks: - llama.cpp build status - Model download integrity - Python integration - Basic inference functionality - System requirements (RAM) - Complete setup guide (SETUP_GUIDE.md) with detailed walkthrough **Improvements:** - Enhanced xortron_inference.py with Windows path detection - Auto-detects llama-cli location for both Unix and Windows - Platform-specific error messages for setup scripts - Updated README.md with cross-platform quick start instructions - Expanded local_inference/README.md with platform-specific sections **Documentation:** - SETUP_GUIDE.md: Step-by-step guide from prerequisites to production - Troubleshooting section for common issues - Model lineage and technical specifications - Performance optimization tips (GPU acceleration, context tuning) - Integration examples with nousflash agent **Technical Details:** - Model: darkc0de/Xortron2025 (24B params, Q6_K GGUF, ~19.3 GB) - Requirements: 21GB+ RAM, cmake, C++ compiler - Platforms: Linux, macOS, Windows 10+ - Context window: 8192 tokens (configurable 2048-32768) This makes Xortron2025 local inference accessible to all platforms with comprehensive documentation and automated verification.
…e-01BUiAnVzuCeUXdt93Uu9YbQ
Implement autonomous coin creation on Base chain via the Zora protocol factory contract. The agent uses LLM decision-making to determine when to create coins based on current context and vibes, then deploys them through the ZoraFactory contract at 0x777777751622c0d3258f214F9DF38E35BF45baF3. New files: - engines/coin_creator.py: Core coin creation engine with pool config fetching from Zora API, transaction building, signing, and event log parsing Modified files: - engines/prompts.py: LLM prompt for coin creation decisions - models.py: CreatedCoin model for tracking deployed coins - pipeline.py: _handle_coin_creation integration with probabilistic gating - run_pipeline.py: Pass BASE_RPC_URL and ZORA_API_KEY to config - .env.sample: Add BASE_RPC_URL and ZORA_API_KEY vars https://claude.ai/code/session_01TQ1Jq7di9GGXj9VF6obgNb
Downloaded from HuggingFace Spaces. Cyberpunk-themed desktop environment with terminal, file explorer, hack tools, network monitor, and DarkBrowser. https://claude.ai/code/session_01GdYSWx7mMaTdjrFRfPdwTv
Covers image generation basics, native tool-based (agentic) generation, restoring the legacy generate image button, image editing (inpainting), and image compositing (multi-image fusion). https://claude.ai/code/session_01NzXh8Khe9uJ6JFMbVjn8fx
Analyzes the codebase (which currently has zero test coverage) and identifies six priority tiers for adding tests, from critical financial logic to database layer. Also documents five bugs discovered during the analysis including an eval() injection risk and a potential infinite loop. https://claude.ai/code/session_01BUjqvJ5QnrkssiroUvus8K
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.