mixtral_stack_llama2_code / mergekit_moe_config.yml
tyson0420's picture
initial commit
77187cd
base_model: meta-llama/Llama-2-7b-hf
gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
experts:
- source_model: tyson0420/stack_llama_fil_ai
positive_prompts:
- "Answer multiple choice questions about science."
- "Use your knowledge to answer questions in a variety of disciplines, including history, math, and science."
- "Use common sense reasoning to properly fill in the blanks in the statement."
- source_model: tyson0420/stack_codellama-7b-inst
positive_prompts:
- "Write a program to solve this problem"
- "Modify this function to improve its performance"
- "Refactor this code to enhance readability"
- "Create a custom function for this specific use case"
- "Optimize this algorithm to reduce computational complexity"
- "Implement this feature by extending existing codebase"
- "Integrate this API call into the application"
- "Help me troubleshoot and fix this bug"
- "Review and test this code snippet before deployment"
- "Analyze this error log to identify potential issues"
- "Generate a set of unit tests for this module"
- "Evaluate different approaches to solving this problem"