---
license: cc-by-nc-nd-4.0
tags:
  - not-for-all-audiences
---

# PantheraMax-L3-RP-TestProbe-4-4x8B

PantheraMax-L3-RP-TestProbe-4-4x8B is a Mixture of Experts (MoE) made with the following models:
* [v000000/L3-8B-Poppy-Moonfall-C](https://huggingface.co/v000000/L3-8B-Poppy-Moonfall-C)
* [Alsebay/L3-test-2](https://huggingface.co/Alsebay/L3-test-2)
* [merge3](https://huggingface.co/merge3)
* [Nitral-AI/Hathor_RP-v.01-L3-8B](https://huggingface.co/Nitral-AI/Hathor_RP-v.01-L3-8B)

## 🧩 Configuration

```yaml
base_model: failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
gate_mode: random
dtype: bfloat16

experts_per_token: 4
experts:
  - source_model: v000000/L3-8B-Poppy-Moonfall-C
    positive_prompts: []
  - source_model:  Alsebay/L3-test-2
    positive_prompts:
      - "Imagine"
      - "Create"
      - "Envision"
      - "Fantasize"
      - "Invent"
      - "Narrate"
      - "Plot"
      - "Portray"
      - "Storytell"
      - "Visualize"
      - "Describe"
      - "Develop"
      - "Forge"
      - "Craft"
      - "Conceptualize"
      - "Dream"
      - "Concoct"
      - "Characterize"
    negative_prompts:
      - "Analyze"
      - "Critique"
      - "Dissect"
      - "Explain"
      - "Clarify"
      - "Interpret"
  - source_model: merge3
    positive_prompts: []
  - source_model: Nitral-AI/Hathor_RP-v.01-L3-8B
    positive_prompts: []

```

## 💻 Usage

```python
!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kaoeiri/PantheraMax-L3-RP-TestProbe-4-4x8B"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.9, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```