!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Eurdem/megatron_2.1_MoE_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=1000, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	76.64
AI2 Reasoning Challenge (25-Shot)	72.95
HellaSwag (10-Shot)	88.94
MMLU (5-Shot)	64.56
TruthfulQA (0-shot)	78.20
Winogrande (5-shot)	84.53
GSM8k (5-shot)	70.66