jtatman/TinyDolphin-3x-MoE

base_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
gate_mode: hidden
dtype: float16
experts:
  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
    positive_prompts: 
    - "think step-by-step and follow these instructions"
    - "read the following passage, and summarize it in less than 30 words."
    - "please answer this question, consider the options carefully, and return the most likely answer."
  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
    positive_prompts: ["produce python code"]
  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
    positive_prompts: ["What is 2 x 22?"]

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jtatman/TinyDolphin-3x-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"])