metadata

license: apache-2.0
tags:
  - moe
  - merge

Megatron_v3_2x7B

Megatron_v3_2x7B is a Mixure of Experts (MoE).

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Eurdem/Megatron_v4_2x7B"

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": "Tell me about AI"}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=1024, do_sample=True, temperature=0.7, top_k=500, top_p=0.95)
print(outputs[0]["generated_text"])