Downloads · 30 days
26
0% of all-time downloads
Nitral-Archive/Prima-Pastacles-7b
Prima-Pastacles-7b is a text generation model from Nitral-Archive. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Downloads · 30 days
26
0% of all-time downloads
All-time downloads
7.2K
Public
Parameters
7.2B
14.5 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README
Quants Thanks to @Nold and @Bartowski:
https://huggingface.co/nold/Prima-Pastacles-7b-GGUF
https://huggingface.co/bartowski/Prima-Pastacles-7b-exl2
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: Test157t/Pasta-PrimaMaid-7b
layer_range: [0, 32]
- model: Locutusque/Hercules-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: Test157t/Pasta-PrimaMaid-7b
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.91 |
| AI2 Reasoning Challenge (25-Shot) | 66.04 |
| HellaSwag (10-Shot) | 85.83 |
| MMLU (5-Shot) | 64.21 |
| TruthfulQA (0-shot) | 56.69 |
| Winogrande (5-shot) | 79.64 |
| GSM8k (5-shot) | 55.04 |