Rulga/status-law-gbot at 3b59cc2880e6b4798ac5b4b5207e71abee3d6cbf

254 kB

2 contributors

Enhance training method in FineTuner: Add detailed logging for training process, dataset loading, tokenization, and error handling to improve debugging and traceability.

3b59cc2 8 months ago

analytics
Add analizer and tuner bot 9 months ago
chat_history
Upload chat_history/.gitkeep with huggingface_hub 9 months ago
config
Refactor training data export function and add dataset structure repair tool 8 months ago
src
Enhance training method in FineTuner: Add detailed logging for training process, dataset loading, tokenization, and error handling to improve debugging and traceability. 8 months ago
tools
Refactor training data export function and add dataset structure repair tool 8 months ago
utils
Initialize project structure and add configuration for knowledge base and document loading 9 months ago
vector_store
Upload vector_store/.gitkeep with huggingface_hub 9 months ago
web
Refactor evaluation interface: Update label for evaluated pairs checkbox and improve documentation for QA pairs dataframe function. 8 months ago
.gitattributes

3.52 kB

Resolve merge conflict in .gitattributes for improved clarity 9 months ago
.gitignore

462 Bytes

Refactor paths in configuration and .gitignore for chat history and model management 8 months ago
README.md

4.8 kB

Refine README.md for clarity and accuracy in feature descriptions, enhance multilingual support details, and update project structure information. 8 months ago
app.py

55.9 kB

Refactor fine-tuning process: Update function to utilize evaluated chat history and improve error handling for training data preparation. 8 months ago
dataset.py

1.76 kB

Refactor training data export function and add dataset structure repair tool 8 months ago
repair-script.py

8.23 kB

Refactor app layout and add repair script for conversation IDs 8 months ago
repair_conversation_ids.log

27.4 kB

Refactor app layout and add repair script for conversation IDs 8 months ago
repair_dataset_structure.log

26.9 kB

Refactor training data export function and add dataset structure repair tool 8 months ago
requirements.txt

384 Bytes

Add language detection to response generation and update system message accordingly 8 months ago
terminal

758 Bytes

Add dataset configuration files and scripts 9 months ago
test_endpoint.py

1.02 kB

Refactor API client initialization and add comprehensive API configuration settings 8 months ago