Downloads · 30 days
55
0% of all-time downloads
Weyaxi/OpenHermes-2.5-neural-chat-v3-2-Slerp
OpenHermes-2.5-neural-chat-v3-2-Slerp is a text generation model from Weyaxi. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
55
0% of all-time downloads
All-time downloads
14.6K
Public
Parameters
7.2B
14.5 GB on disk
Likes
27
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README

Use this instead:
https://hf.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp

This is the model for OpenHermes-2.5-neural-chat-v3-2-Slerp. I used mergekit to merge models.
You can use these prompt templates, but I recommend using ChatML.
<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>
### System:
{system}
### User:
{user}
### Assistant:
slices:
- sources:
- model: teknium/OpenHermes-2.5-Mistral-7B
layer_range: [0, 32]
- model: Intel/neural-chat-7b-v3-2
layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
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 # fallback for rest of tensors
dtype: float16
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 70.2 |
| ARC (25-shot) | 67.49 |
| HellaSwag (10-shot) | 85.42 |
| MMLU (5-shot) | 64.13 |
| TruthfulQA (0-shot) | 61.05 |
| Winogrande (5-shot) | 80.3 |
| GSM8K (5-shot) | 63.08 |