base_model: openaccess-ai-collective/tiny-mistral
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: openaccess-ai-collective/tiny-mistral
    positive_prompts:
      - "math"
    # You can add negative_prompts if needed
  - source_model: openaccess-ai-collective/tiny-mistral

    positive_prompts:
      - "science"
  - source_model: openaccess-ai-collective/tiny-mistral
    positive_prompts:
      - "writing"
    # You can add negative_prompts if needed
  - source_model: openaccess-ai-collective/tiny-mistral
    positive_prompts:
      - "general"

💻 Usage

python

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "JSpergel/test_tiny_mixtral_only_router_2"

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"])