megatron_v1/README.md

license, tags, model-index

license	tags	model-index
apache-2.0	moe merge	name results megatron_v1 task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 65.96 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 84.8 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 65.02 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 60.32 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 79.79 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_v1 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 57.01 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_v1 Open LLM Leaderboard

megatron_v1

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

💻 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