---
base_model:
- Nitral-AI/Poppy-1.35-Phase1
- Nitral-AI/Pp-72xra1
library_name: transformers
tags:
- mergekit
- merge
license: other
language:
- en
---
**Exllamav2** quant (**exl2** / **3.0 bpw**) made with ExLlamaV2 v0.1.3
Other EXL2 quants:
| **Quant** | **Model Size** | **lm_head** |
| ----- | ---------- | ------- |
|
**[2.2](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-2_2bpw_exl2)** | 3250 MB | 6 |
|**[2.5](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-2_5bpw_exl2)** | 3478 MB | 6 |
|**[3.0](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-3_0bpw_exl2)** | 3894 MB | 6 |
|**[3.5](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-3_5bpw_exl2)** | 4311 MB | 6 |
|**[3.75](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-3_75bpw_exl2)** | 4518 MB | 6 |
|**[4.0](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-4_0bpw_exl2)** | 4727 MB | 6 |
|**[4.25](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-4_25bpw_exl2)** | 4935 MB | 6 |
|**[5.0](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-5_0bpw_exl2)** | 5559 MB | 6 |
|**[6.0](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-6_0bpw_exl2)** | 6489 MB | 8 |
|**[6.5](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-6_5bpw_exl2)** | 6909 MB | 8 |
|**[8.0](https://huggingface.co/Zoyd/Nitral-AI_Poppy_Porpoise-1.4-L3-8B-8_0bpw_exl2)** | 8123 MB | 8 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/Boje781GkTdYgORTYGI6r.png)
# "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences.
# Note: This variant is an attempt to get something closer to 0.72 while maintaining the improvements of 1.30.
# : [Presets in repo folder](https://huggingface.co/Nitral-AI/Poppy_Porpoise-1.0-L3-8B/tree/main/Porpoise_1.0-Presets).
# If you want to use vision functionality: You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp). And need to load the specified **mmproj** file: [Llava MMProj](https://huggingface.co/Nitral-AI/Llama-3-Update-2.0-mmproj-model-f16).
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: Nitral-AI/Pp-72xra1
layer_range: [0, 32]
- model: Nitral-AI/Poppy-1.35-Phase1
layer_range: [0, 32]
merge_method: slerp
base_model: Nitral-AI/Pp-72xra1
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
```