Usage:
Use mondk/msh-tiny.For-Test-In-Note-Book-Google-Colab, but change REPO_ID to REPO_ID = "mondk/Msh-Tiny-97M"
Training data
Thanks to:
- mondk/Greetings-hi-for-train-Msh-v2
- tatsu-lab/alpaca
- databricks/databricks-dolly-15k
- teknium/OpenHermes-2.5
- HuggingFaceH4/no_robots
- open-thoughts/OpenThoughts-114k
- google-research-datasets/poem_sentiment
- CohereLabs/aya_dataset
- Wanfq/gpqa
- glaiveai/glaive-function-calling-v2
- FreedomIntelligence/medical-o1-reasoning-SFT
- m-a-p/Code-Feedback
- openai/gsm8k
- HuggingFaceH4/ultrachat_200k
- cais/mmlu
- sentence-transformers/natural-questions
- QuixiAI/dolphin
- openai/openai_humaneval
- google-research-datasets/mbpp
- hendrycks/competition_math