metadata
license: apache-2.0
language:
- en
tags:
- simllama
- llama
- smol-smoltalk
- slm
- 400m
datasets:
- HuggingFaceTB/smol-smoltalk
- exnivo/tinybrain-instruct-sft-200k
- OpenAssistant/oasst2
- OpenAssistant/oasst1
- drwlf/medra-thinking-768
- togethercomputer/llama-instruct
- interview-eval/MATH
- RLAIF/mbpp
Checkpoint info: {'loss': '1.84', 'grad_norm': '0.5195', 'learning_rate': '9.182e-06', 'epoch': '1.082'}
Base model: https://huggingface.co/simonko912/simllama-1.1-base