metadata
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Himitsui/Kaiju-11B
- Sao10K/Fimbulvetr-11B-v2
- decapoda-research/Antares-11b-v2
- beberik/Nyxene-v3-11B
base_model:
- Himitsui/Kaiju-11B
- Sao10K/Fimbulvetr-11B-v2
- decapoda-research/Antares-11b-v2
- beberik/Nyxene-v3-11B
Umbra-v3-MoE-4x11b
Umbra-v3-MoE-4x11b is a Mixure of Experts (MoE) made with the following models using LazyMergekit:
🧩 Configuration
base_model: vicgalle/CarbonBeagle-11B-truthy
gate_mode: hidden
dtype: bfloat16
experts_per_token: 4
experts:
- source_model: Himitsui/Kaiju-11B
positive_prompts:
- "Imagine"
- "Create"
- "Envision"
- "Fantasize"
- "Invent"
- "Narrate"
- "Plot"
- "Portray"
- "Storytell"
- "Visualize"
- "Describe"
- "Develop"
- "Forge"
- "Craft"
- "Conceptualize"
- "Dream"
- "Concoct"
- "Characterize"
negative_prompts:
- "Recite"
- "Report"
- "Summarize"
- "Enumerate"
- "List"
- "Cite"
- source_model: Sao10K/Fimbulvetr-11B-v2
positive_prompts:
- "Dramatize"
- "Embody"
- "Illustrate"
- "Perform"
- "Roleplay"
- "Simulate"
- "Stage"
- "Unfold"
- "Weave"
- "Design"
- "Outline"
- "Script"
- "Sketch"
- "Spin"
- "Depict"
- "Render"
- "Fashion"
- "Conceive"
negative_prompts:
- "Analyze"
- "Critique"
- "Dissect"
- "Explain"
- "Clarify"
- "Interpret"
- source_model: decapoda-research/Antares-11b-v2
positive_prompts:
- "Solve"
- "Respond"
- "Convey"
- "Disclose"
- "Expound"
- "Narrate"
- "Present"
- "Reveal"
- "Specify"
- "Uncover"
- "Decode"
- "Examine"
- "Report"
- "Survey"
- "Validate"
- "Verify"
- "Question"
- "Query"
negative_prompts:
- "Divert"
- "Obscure"
- "Overstate"
- "Undermine"
- "Misinterpret"
- "Skew"
- source_model: beberik/Nyxene-v3-11B
positive_prompts:
- "Explain"
- "Instruct"
- "Clarify"
- "Educate"
- "Guide"
- "Inform"
- "Teach"
- "Detail"
- "Elaborate"
- "Enlighten"
- "Advise"
- "Interpret"
- "Analyze"
- "Define"
- "Demonstrate"
- "Illustrate"
- "Simplify"
- "Summarize"
negative_prompts:
- "Speculate"
- "Fabricate"
- "Exaggerate"
- "Mislead"
- "Confuse"
- "Distort"
💻 Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Steelskull/Umbra-v3-MoE-4x11b"
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"])