Downloads · 30 days
37
3% of all-time downloads
RichardErkhov/CultriX_-_Qwen2.5-14B-Wernicke-gguf
CultriX_-_Qwen2.5-14B-Wernicke-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
37
3% of all-time downloads
All-time downloads
1.1K
Public
Repo size
150 GB
Likes
0
Public
Click a slice to open those files.
.gguf177 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen2.5-14B-Wernicke - GGUF
| Name | Quant method | Size |
|---|---|---|
| Qwen2.5-14B-Wernicke.Q2_K.gguf | Q2_K | 5.37GB |
| Qwen2.5-14B-Wernicke.Q3_K_S.gguf | Q3_K_S | 6.2GB |
| Qwen2.5-14B-Wernicke.Q3_K.gguf | Q3_K | 6.84GB |
| Qwen2.5-14B-Wernicke.Q3_K_M.gguf | Q3_K_M | 6.84GB |
| Qwen2.5-14B-Wernicke.Q3_K_L.gguf | Q3_K_L | 7.38GB |
| Qwen2.5-14B-Wernicke.IQ4_XS.gguf | IQ4_XS | 7.62GB |
| Qwen2.5-14B-Wernicke.Q4_0.gguf | Q4_0 | 7.93GB |
| Qwen2.5-14B-Wernicke.IQ4_NL.gguf | IQ4_NL | 8.01GB |
| Qwen2.5-14B-Wernicke.Q4_K_S.gguf | Q4_K_S | 7.98GB |
| Qwen2.5-14B-Wernicke.Q4_K.gguf | Q4_K | 8.37GB |
| Qwen2.5-14B-Wernicke.Q4_K_M.gguf | Q4_K_M | 8.37GB |
| Qwen2.5-14B-Wernicke.Q4_1.gguf | Q4_1 | 8.75GB |
| Qwen2.5-14B-Wernicke.Q5_0.gguf | Q5_0 | 9.56GB |
| Qwen2.5-14B-Wernicke.Q5_K_S.gguf | Q5_K_S | 9.56GB |
| Qwen2.5-14B-Wernicke.Q5_K.gguf | Q5_K | 9.79GB |
| Qwen2.5-14B-Wernicke.Q5_K_M.gguf | Q5_K_M | 9.79GB |
| Qwen2.5-14B-Wernicke.Q5_1.gguf | Q5_1 | 10.38GB |
| Qwen2.5-14B-Wernicke.Q6_K.gguf | Q6_K | 11.29GB |
| Qwen2.5-14B-Wernicke.Q8_0.gguf | Q8_0 | 14.62GB |
library_name: transformers tags:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using Qwen/Qwen2.5-14B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.0
- model: Qwen/Qwen2.5-14B-Instruct
- model: arcee-ai/SuperNova-Medius
- model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
- model: v000000/Qwen2.5-Lumen-14B
base_model: Qwen/Qwen2.5-14B
merge_method: model_stock
dtype: bfloat16
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 36.60 |
| IFEval (0-Shot) | 52.35 |
| BBH (3-Shot) | 50.64 |
| MATH Lvl 5 (4-Shot) | 30.06 |
| GPQA (0-shot) | 19.13 |
| MuSR (0-shot) | 18.25 |
| MMLU-PRO (5-shot) | 49.15 |