metadata
license: apache-2.0
base_model:
- Stormtrooperaim/Mystral-Uncensored-RP-7B
- DarkArtsForge/Avnas-7B-v1.1
- mistralai/Mistral-7B-v0.3
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Stormtrooperaim/Mystral-Uncensored-RP-7B
- DarkArtsForge/Avnas-7B-v1.1
- mistralai/Mistral-7B-v0.3
Shadowforge- 3x7B-MoE
Shadowforge-3x7B-MoE is a Mixture of Experts (MoE) made with the following models using LazyMergekit:
This is an UNCENSORED model with NO content restrictions. Users assume ALL RESPONSIBILITY for generated content. Not recommended for production environments or sensitive applications.
use_cases:
- Creative fiction writing without boundaries
- Unrestricted roleplay scenarios
- Exploring controversial topics
- Dark narrative generation
- Taboo subject analysis
- Unfiltered problem solving
💻 Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Stormtrooperaim/Shadowforge-3x7B-MoE"
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=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])