Test merge of 7b models for learning purposees. v0.2 is mostly the same, with minor promting changes and consolidating shards from 1B to 4B to reduce number of files.
Description: This model is a merge of BAAI/Infinity-Instruct-7M-Gen-mistral-7B, SanjiWatsuki/Kunoichi-7B, and uukuguy/speechless-instruct-mistral-7b-v0.2 This is the first model I've ever uploaded and wanted to learn more about the process. Merged using mergekit-moe.
Works up to 8k context, 16k with 2.5 RoPe scaling
Prompt template: Custom format, or Alpaca
Alpaca: Below is an instruction that describes a task. Write a response that appropriately completes the request.
Instruction: {prompt}
Response:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 19.92 |
| IFEval (0-Shot) | 36.36 |
| BBH (3-Shot) | 32.26 |
| MATH Lvl 5 (4-Shot) | 5.66 |
| GPQA (0-shot) | 6.71 |
| MuSR (0-shot) | 13.26 |
| MMLU-PRO (5-shot) | 25.25 |
- Downloads last month
- 11
Model tree for Jacoby746/Inf-Silent-Kunoichi-v0.2-2x7B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard36.360
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard32.260
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard5.660
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.710
- acc_norm on MuSR (0-shot)Open LLM Leaderboard13.260
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard25.250