someone on Nostr: Coding and math datasets that I used to convert base llama 3.1 to instruct: - ...

Coding and math datasets that I used to convert base llama 3.1 to instruct:

- nickrosh/Evol-Instruct-Code
- m-a-p/CodeFeedback-Filtered-Instruction
- yingyingzhang/metamath-qwen2-math
- cognitivecomputations/dolphin-coder
- iamtarun/python_code_instructions_18k_alpaca
- OpenCoder-LLM/opc-sft-stage2

Param count: 8B
Tool used: Unsloth
GPU: A6000
Target modules: all including embed_tokens and lm_head