README.md

metadata

license: apache-2.0
tags:
  - moe
  - frankenmoe
  - merge
  - mergekit
  - lazymergekit
  - starsnatched/MemGPT-DPO
  - starsnatched/MemGPT-3
  - starsnatched/MemGPT
base_model:
  - starsnatched/MemGPT-DPO
  - starsnatched/MemGPT-3
  - starsnatched/MemGPT

Memgpt-3x7b-MOE

Memgpt-3x7b-MOE is a Mixure of Experts (MoE) made with the following models using LazyMergekit:

• starsnatched/MemGPT-DPO
• starsnatched/MemGPT-3
• starsnatched/MemGPT

🧩 Configuration

base_model: liminerity/Memgpt-slerp-7b-5
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: starsnatched/MemGPT-DPO
    positive_prompts:
    - "versatile"
    - "helpful"
    - "factual"
    - "integrated"
    - "adaptive"
    - "comprehensive"
    - "balanced"
    negative_prompts:
    - "specialized"
    - "narrow"
    - "focused"
    - "limited"
    - "specific"

  - source_model: starsnatched/MemGPT-3
    positive_prompts:
    - "analytical"
    - "accurate"
    - "logical"
    - "knowledgeable"
    - "precise"
    - "calculate"
    - "compute"
    - "solve"
    - "work"
    - "python"
    - "javascript"
    - "programming"
    - "algorithm"
    - "tell me"
    - "assistant"
    negative_prompts:
    - "creative"
    - "abstract"
    - "imaginative"
    - "artistic"
    - "emotional"
    - "mistake"
    - "inaccurate"

  - source_model: starsnatched/MemGPT
    positive_prompts:
    - "instructive"
    - "clear"
    - "directive"
    - "helpful"
    - "informative"
    negative_prompts:
    - "exploratory"
    - "open-ended"
    - "narrative"
    - "speculative"
    - "artistic"

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "liminerity/Memgpt-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"])