metadata
pipeline_tag: text-generation
inference: false
license: cc-by-nc-4.0
library_name: transformers
model-index:
- name: ibm/PowerMoE-3b
results:
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: ARC
metrics:
- name: accuracy-norm
type: accuracy-norm
value: 54.8
verified: false
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: BoolQ
metrics:
- name: accuracy
type: accuracy
value: 67.1
verified: false
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: Hellaswag
metrics:
- name: accuracy-norm
type: accuracy-norm
value: 70.3
verified: false
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: OpenBookQA
metrics:
- name: accuracy-norm
type: accuracy-norm
value: 38.4
verified: false
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: PIQA
metrics:
- name: accuracy-norm
type: accuracy-norm
value: 77.5
verified: false
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: Winogrande
metrics:
- name: accuracy-norm
type: accuracy-norm
value: 64.6
verified: false
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: MMLU
metrics:
- name: accuracy
type: accuracy
value: 33.4
verified: false
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: GSM8k (5 shot)
metrics:
- name: accuracy
type: accuracy
value: 27.2
verified: false
- task:
type: text-generation
dataset:
type: lm-eval-harness
name: math (4 shot)
metrics:
- name: accuracy
type: accuracy
value: 10
verified: false
- task:
type: text-generation
dataset:
type: bigcode-eval
name: humaneval
metrics:
- name: pass@1
type: pass@1
value: 15.2
verified: false
- task:
type: text-generation
dataset:
type: bigcode-eval
name: MBPP
metrics:
- name: pass@1
type: pass@1
value: 24
verified: false
Model Summary
PowerMoE-3B is a 3B sparse Mixture-of-Experts (sMoE) language model trained with the Power learning rate scheduler. It sparsely activates 800M parameters for each token. It is trained on a mix of open-source and proprietary datasets. PowerMoE-3B has shown promising results compared to other dense models with 2x activate parameters across various benchmarks, including natural language multi-choices, code generation, and math reasoning. Paper: https://arxiv.org/abs/2408.13359
Usage
Note: requires a custom branch of transformers: https://github.com/mayank31398/transformers/tree/granitemoe
Generation
This is a simple example of how to use PowerMoE-3b model.
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # or "cpu"
model_path = "ibm/PowerMoE-3b"
tokenizer = AutoTokenizer.from_pretrained(model_path)
# drop device_map if running on CPU
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()
# change input text as desired
prompt = "Write a code to find the maximum value in a list of numbers."
# tokenize the text
input_tokens = tokenizer(prompt, return_tensors="pt")
# transfer tokenized inputs to the device
for i in input_tokens:
input_tokens[i] = input_tokens[i].to(device)
# generate output tokens
output = model.generate(**input_tokens, max_new_tokens=100)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# loop over the batch to print, in this example the batch size is 1
for i in output:
print(i)