README.md

metadata

license: apache-2.0
tags:
  - moe
  - mergekit
  - merge
  - chinese
  - arabic
  - english
  - multilingual
  - german
  - french
  - jondurbin/bagel-dpo-34b-v0.2
  - jondurbin/nontoxic-bagel-34b-v0.2

MetaModel_moe_yix2

This model is a Mixure of Experts (MoE) made with mergekit (mixtral branch). It uses the following base models:

• jondurbin/bagel-dpo-34b-v0.2
• jondurbin/nontoxic-bagel-34b-v0.2

🧩 Configuration

dtype: bfloat16
experts:
- positive_prompts:
  - chat
  - assistant
  - tell me
  - explain
  source_model: jondurbin/bagel-dpo-34b-v0.2
- positive_prompts:
  - chat
  - assistant
  - tell me
  - explain
  source_model: jondurbin/nontoxic-bagel-34b-v0.2
gate_mode: hidden

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "gagan3012/MetaModel_moe_yix2"

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"])