3 items • Updated
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_2025,
author = { Sthenno and Jiayu Wang },
title = { miscii-14b-0218 (Revision 6f78859) },
year = 2025,
url = { https://huggingface.co/sthenno-com/miscii-14b-0218 },
doi = { 10.57967/hf/7297 },
publisher = { Hugging Face }
}
- Downloads last month
- 26
Safetensors
Model size
15B params
Tensor type
BF16
·
Model tree for sthenno-com/miscii-14b-0218
Merge model
this model
Space using sthenno-com/miscii-14b-0218 1
Collection including sthenno-com/miscii-14b-0218
Paper for 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
