Update the LOCAL_DIR variable to use a relative path ("./") instead of an absolute Windows path. This improves portability and simplifies setup for different environments. Also remove the UTF-8 BOM character from the import line.
docs: update README to use relative paths and clarify sync script
- Replace absolute Windows path with relative path for local directory references.
- Clarify that the sync script requires HF_TOKEN and HF_REPO_ID environment variables.
- Minor formatting fix: remove UTF-8 BOM from the first line.
Add comprehensive model card for Hugging Face repository, including model
description, technical details, usage examples, safety disclaimers, and
license information. This provides proper documentation for the
Cogni-OpenModel deployment on the Hugging Face platform.
feat(tools): add script to sync README to Hugging Face Hub
Uploads the local README.hf.md file as README.md to a specified Hugging Face repository. This automates the documentation update process for the model hub.
chore: rename project from CogniXpert-Model-v1.0 to Cogni-OpenModel
- Update all references in README.md, app.py, CONTRIBUTING.md, CODE_OF_CONDUCT.md
- Update LOCAL_DIR paths, page titles, system prompts, and headings
- Also update CONTRIBUTING.md license reference from AGPL-3.0 to MIT
- Replace LICENSE file with MIT License text (Copyright 2024 CogniX LTD)
- License scoped to LoRA adapter weights, config files, and source code
- Add explicit note that Meta Llama 3.1 8B base model remains under
Meta's Llama 3.1 Community License Agreement
- Update README.md license badge from AGPL-3.0 to MIT
- Expand license section with clear scope and base-model carve-out
This commit adds the full text of the GNU Affero General Public License version 3 to the project, ensuring compliance with copyleft requirements for network server software.
build: add initial config for unsloth/meta-llama-3.1-8b-bnb-4bit model
Add a standardized pull request template to ensure consistent PR descriptions and required checklists. This helps maintain quality and documentation standards across contributions.
docs: add SECURITY.md file with vulnerability reporting policy
Add comprehensive documentation including model details, usage examples,
hardware requirements, safety considerations, and contribution guidelines.
The update provides clear instructions for both base model and LoRA adapter usage,
along with licensing information and acknowledgments.
docs: add README.hf.md with model documentation and usage
Add CONTRIBUTING.md file with contribution guidelines, development setup instructions, pull request guidelines, coding style recommendations, and safety considerations for the CogniXpert project
Implement a chat interface using Streamlit that loads a Meta Llama 3 model
with optional LoRA adapter support. The interface includes:
- Chat history persistence
- Configurable system prompt
- Generation parameters (temperature, top-p, max tokens)
- Proper message formatting for the model
chore: add gitattributes file for LFS configuration
