Quantization made by Richard Erkhov.
TinyLlama-1.1B-1T-OpenOrca - GGUF
- Model creator: https://huggingface.co/jeff31415/
- Original model: https://huggingface.co/jeff31415/TinyLlama-1.1B-1T-OpenOrca/
Original model description:
license: apache-2.0 datasets: - Open-Orca/OpenOrca - bigcode/starcoderdata - cerebras/SlimPajama-627B language: - en
Base model:
PY007/TinyLlama-1.1B-intermediate-step-480k-1T
Dataset:
Fine tuned on OpenOrca GPT4 subset for 1 epoch,Using CHATML format
Model License:
Apache 2.0, following the TinyLlama base model.
Quantisation:
- GPTQ:https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-GPTQ
- AWQ:https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-AWQ
- GGUF:https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-GGUF
Hardware and training details:
Hardware: 1*RTX A5000, ~16 hours to complete 1 epoch. GPU from autodl.com, cost around $3 for this finetuning. https://wandb.ai/jeff200402/TinyLlama-Orca?workspace= for more details.