miscii-14b-0218
“I think there’s a reason I’m a shadow, but she looks like an angel.” — Viyella’s Memory, excerpted from The Angel’s Message by Laur (2018).
Technical Specifications
miscii-14b-0218 is a fine-tuned model based on Qwen/Qwen2.5-14B-Instruct (Qwen Team, 2024). It is developed using Arcee’s MergeKit (Goddard et al. 2024), employing the Model Stock merge method (Jang, Yun, and Han 2024). The integration utilized tempesthenno-ppo-enchanted as the base model.
The configuration parameters for generating miscii-14b-0218 are documented below:
name: miscii-14b-0218
merge_method: model_stock
base_model: tempesthenno-ppo-enchanted
tokenizer:
source: base
dtype: float32
out_dtype: bfloat16
parameters:
int8_mask: true
normalize: true
rescale: false
models:
- model: tempesthenno-sft-0218-ckpt60
- model: tempesthenno-sft-0218-ckpt80
- model: tempesthenno-sft-0218-stage2-ckpt40
- model: tempesthenno-sft-0218-stage2-ckpt50
- model: tempesthenno-sft-0218-stage2-ckpt60
Citation
If you find miscii-14b-0218 useful for your research and applications, please use the following citation formats:
BibTeX
@misc{sthenno-com_2025,
author = {{sthenno-com}},
title = {miscii-14b-0218 (Revision 92a6e4a)},
year = 2025,
url = {https://huggingface.co/sthenno-com/miscii-14b-0218},
doi = {10.57967/hf/4780},
publisher = {HF中国镜像站}
}
Plain Text
Please cite as: sthenno-com. miscii-14b-0218 (Revision b1a04d4). HF中国镜像站, 2025. https://huggingface.co/sthenno-com/miscii-14b-0218.
- Downloads last month
- 1,417
Model tree for sthenno-com/miscii-14b-0218
Space using sthenno-com/miscii-14b-0218 1
Collection including sthenno-com/miscii-14b-0218
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard76.560
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard50.640
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard51.440
- acc_norm on GPQA (0-shot)Open LLM Leaderboard17.790
- acc_norm on MuSR (0-shot)Open LLM Leaderboard13.210
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard47.750