UndeadWizard / README.md
blueprintninja's picture
Upload folder using huggingface_hub
d73dabe verified
|
raw
history blame
1.74 kB
metadata
license: apache-2.0
tags:
  - moe
  - frankenmoe
  - merge
  - mergekit
  - lazymergekit
  - cognitivecomputations/WizardLM-7B-Uncensored
  - dreamgen/WizardLM-2-7B
base_model:
  - cognitivecomputations/WizardLM-7B-Uncensored
  - dreamgen/WizardLM-2-7B

UndeadWizard

UndeadWizard is a Mixture of Experts (MoE) made with the following models using LazyMergekit:

🧩 Configuration

base_model: dreamgen/WizardLM-2-7B
experts:
  - source_model: cognitivecomputations/WizardLM-7B-Uncensored
    positive_prompts:
    - "chat"
    - "write"
    - "scene"
    - "story"
    - "explain"
  - source_model: dreamgen/WizardLM-2-7B
    positive_prompts:
    - "reason"
    - "math"
    - "code"
    - "solve"
    - "python"

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "blueprintninja/UndeadWizard"

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"])