megatron_1.1_MoE_2x7B
megatron_1.1_MoE_2x7B is a Mixure of Experts (MoE) (mistral)
π» Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Eurdem/megatron_1.1_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=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. | 69.94 |
AI2 Reasoning Challenge (25-Shot) | 65.53 |
HellaSwag (10-Shot) | 84.52 |
MMLU (5-Shot) | 65.02 |
TruthfulQA (0-shot) | 51.58 |
Winogrande (5-shot) | 81.53 |
GSM8k (5-shot) | 71.49 |
- Downloads last month
- 977
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.
Model tree for Eurdem/megatron_1.1_MoE_2x7B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard65.530
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard84.520
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.020
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard51.580
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard81.530
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard71.490