base_model: mlabonne/Marcoro14-7B-slerp
dtype: bfloat16
experts:
- positive_prompts:
  - chat
  - assistant
  - tell me
  - explain
  source_model: openchat/openchat-3.5-1210
- positive_prompts:
  - code
  - python
  - javascript
  - programming
  - algorithm
  source_model: beowolx/CodeNinja-1.0-OpenChat-7B
- positive_prompts:
  - storywriting
  - write
  - scene
  - story
  - character
  source_model: maywell/PiVoT-0.1-Starling-LM-RP
- positive_prompts:
  - reason
  - math
  - mathematics
  - solve
  - count
  source_model: WizardLM/WizardMath-7B-V1.1
- positive_prompts:
  - korean
  - answer in korean
  - korea
  source_model: davidkim205/komt-mistral-7b-v1
- positive_prompts:
  - chinese
  - china
  - answer in chinese
  source_model: OpenBuddy/openbuddy-zephyr-7b-v14.1
- positive_prompts:
  - hindi
  - india
  - hindu
  - answer in hindi
  source_model: manishiitg/open-aditi-hi-v1
- positive_prompts:
  - german
  - germany
  - answer in german
  - deutsch
  source_model: VAGOsolutions/SauerkrautLM-7b-v1-mistral
gate_mode: hidden

💻 Usage

python

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "gagan3012/MetaModel_moe_multilingualv1"

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"])