Edit model card

megatron_v1

megatron_v1 is a Mixure of Experts (MoE) made of mistral models.

πŸ’» Usage

from transformers import AutoTokenizer
import transformers
import torch

model = "Eurdem/megatron_v1"

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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 68.82
AI2 Reasoning Challenge (25-Shot) 65.96
HellaSwag (10-Shot) 84.80
MMLU (5-Shot) 65.02
TruthfulQA (0-shot) 60.32
Winogrande (5-shot) 79.79
GSM8k (5-shot) 57.01
Downloads last month
1,255
Safetensors
Model size
12.9B params
Tensor type
BF16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Evaluation results