Update README.md

Updated ReadMe

Add hackathon tags to README

Renamed video file

Updated ReadMe

Updated Gradio SDK version

Updated ReadMe

Track demo video with Xet

Update README dataset statistics

Refactor UI examples, add multi-turn and deflection dataset examples, and implement context checks

refactor: normalize prompt generation, implement robust section parsing, and update inference parameters for stability

fix: update tokenizer handling to avoid model config mismatch warning and align pad_token_id with eos_token_id

fix: use pad_token_id to avoid token registry warning, drop redundant dtype in from_pretrained

fix: use Image.add_local_file() — correct Modal 1.x API to embed dataset.py

fix: replace removed modal.Mount with Image.copy_local_file() for Modal 1.x

chore: clean up run.sh — scope cleanup to project root, improve readability

refactor: split flat root into env/, core/, ui/ domain packages

fix: mount modal/ dir so dataset.py is importable in container, expand cache cleanup to repo root

feat: restructure remote training files under modal/ and expand synthetic CBT dataset

chore: use dtype instead of deprecated torch_dtype and call volume.commit() in tune.py

chore: remove redundant virtual environment activation calls from run.sh

chore: remove obsolete examples directory and update README.md references

chore: remove local pip cache configuration and add console logging during setup

chore: activate python virtual environment in run.sh

feat: redesign app layout with side-by-side coach panel, glassmorphic CBT cards, reduced purple label highlights, and native Gradio responsiveness

Fix chatbot message lag, balance left/right heights, move analysis cards to dynamic bottom section

Fix UI styling: kicker padding, centering, and vertical formatting of list items in output cards

Load fine-tuned LoRA adapter in inference via PeftModel

Remove debug code, restore train_lora as local entrypoint

Debug: add test_token function to verify HF secret injection

Fix tune.py: add explicit huggingface_hub login() before push_to_hub

Fix tune.py: rename max_seq_length to max_length, inject HF_TOKEN Modal secret

Fix tune.py: use SFTConfig instead of TrainingArguments for trl compatibility

Fix tune.py: move container-only ML imports inside Modal remote function body

Refactor codebase to enforce top-level imports, clean comments, remove inline ignores, and expand UI examples

Implement interactive CBT chatbot, glassmorphic card dashboard, and expand training dataset

Remove local keyword heuristics and replace with clean error strings

Remove cloud model tuner UI tab and related bridge code

Fix Gradio 6.0 theme deprecation warning

Add 1-click cloud model tuner Gradio interface and fix README paths

Fix Hugging Face frontmatter color validation

Refactor core codebase to SOLID principles, rename repo URLs to innerspace, and update requirements/gitignore

Pivot subproject to InnerSpace: Offline Smart Journal & Cognitive Coach

Switch model to openbmb/MiniCPM5-1B-SFT for standard Llama compatibility

Fix transformers compatibility issues for local execution

Log local execution exception tracebacks to console for debugging

Filter logging records from transformers containing GenerationMixin to suppress warnings

Broaden warnings filter to suppress transformers GenerationMixin warning across all categories

Ignore transformers GenerationMixin deprecation warning for third-party OpenBMB code

Add simple env loader on import and catch file/PDF parsing exceptions gracefully