metadata

license: apache-2.0
tags:
  - moe
  - frankenmoe
  - merge
  - mergekit
  - lazymergekit
  - Locutusque/TinyMistral-248M-v2.5-Instruct
  - Locutusque/TinyMistral-248M-v2.5-Instruct
  - Locutusque/TinyMistral-248M-v2.5-Instruct
  - Locutusque/TinyMistral-248M-v2.5-Instruct
base_model:
  - Locutusque/TinyMistral-248M-v2.5-Instruct
  - Locutusque/TinyMistral-248M-v2.5-Instruct
  - Locutusque/TinyMistral-248M-v2.5-Instruct
  - Locutusque/TinyMistral-248M-v2.5-Instruct

TinyMistral-248m-v2.5-4x-Moe

TinyMistral-248m-v2.5-4x-Moe is a Mixure of Experts (MoE) made with the following models using LazyMergekit:

🧩 Configuration

base_model: Locutusque/TinyMistral-248M-v2.5
experts:
  - source_model: Locutusque/TinyMistral-248M-v2.5-Instruct
    positive_prompts:
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
    negative_prompts:
      - "Assist me with writing a program that"
      - "How do you"
      - "Explain the concept of"
      - "Give an overview of"
      - "Compare and contrast between"
      - "Provide information about"
      - "Help me understand"
      - "Summarize"
      - "Make a recommendation on"
      - "Answer this question"
  - source_model: Locutusque/TinyMistral-248M-v2.5-Instruct
    positive_prompts:
      - "Assist me with writing a program that"
      - "How do you"
      - "Explain the concept of"
      - "Give an overview of"
    negative_prompts:
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
      - "Compare and contrast between"
      - "Provide information about"
      - "Help me understand"
      - "Summarize"
      - "Make a recommendation on"
      - "Answer this question"
  - source_model: Locutusque/TinyMistral-248M-v2.5-Instruct
    positive_prompts:
      - "Compare and contrast between"
      - "Provide information about"
      - "Help me understand"
    negative_prompts:
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
      - "Assist me with writing a program that"
      - "How do you"
      - "Explain the concept of"
      - "Give an overview of"
      - "Summarize"
      - "Make a recommendation on"
      - "Answer this question"
  - source_model: Locutusque/TinyMistral-248M-v2.5-Instruct
    positive_prompts:
      - "Summarize"
      - "Make a recommendation on"
      - "Answer this question"
    negative_prompts:
      - "Help me debug this code."
      - "Optimize this C# script."
      - "Implement this feature using JavaScript."
      - "Convert this HTML structure into a more efficient design."
      - "Assist me with writing a program that"
      - "How do you"
      - "Explain the concept of"
      - "Give an overview of"
      - "Compare and contrast between"
      - "Provide information about"
      - "Help me understand"
gate_mode: hidden

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jtatman/TinyMistral-248m-v2.5-4x-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"])