README.md

metadata

pipeline_tag: text-generation
inference: false
license: cc-by-nc-4.0
library_name: transformers
model-index:
  - name: ibm/PowerLM-3b
    results:
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: ARC
        metrics:
          - name: accuracy-norm
            type: accuracy-norm
            value: 57.2
            verified: false
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: BoolQ
        metrics:
          - name: accuracy
            type: accuracy
            value: 75
            verified: false
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: Hellaswag
        metrics:
          - name: accuracy-norm
            type: accuracy-norm
            value: 74.2
            verified: false
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: OpenBookQA
        metrics:
          - name: accuracy-norm
            type: accuracy-norm
            value: 41.2
            verified: false
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: PIQA
        metrics:
          - name: accuracy-norm
            type: accuracy-norm
            value: 79.9
            verified: false
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: Winogrande
        metrics:
          - name: accuracy-norm
            type: accuracy-norm
            value: 66.3
            verified: false
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: MMLU
        metrics:
          - name: accuracy
            type: accuracy
            value: 44.3
            verified: false
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: GSM8k (5 shot)
        metrics:
          - name: accuracy
            type: accuracy
            value: 35.9
            verified: false
      - task:
          type: text-generation
        dataset:
          type: lm-eval-harness
          name: math (4 shot)
        metrics:
          - name: accuracy
            type: accuracy
            value: 14
            verified: false
      - task:
          type: text-generation
        dataset:
          type: bigcode-eval
          name: humaneval
        metrics:
          - name: pass@1
            type: pass@1
            value: 21.9
            verified: false
      - task:
          type: text-generation
        dataset:
          type: bigcode-eval
          name: MBPP
        metrics:
          - name: pass@1
            type: pass@1
            value: 28
            verified: false

Model Summary

PowerLM-3B is a 3B state-of-the-art small language model trained with the Power learning rate scheduler. It is trained on a mix of open-source and proprietary datasets. PowerLM-3B has shown promising results compared to other models in the size categories across various benchmarks, including natural language multi-choices, code generation, and math reasoning. Paper: https://arxiv.org/abs/2408.13359

Usage

Note: Requires installing HF transformers from source.

Generation

This is a simple example of how to use PowerLM-3b model.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # or "cpu"
model_path = "ibm/PowerLM-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)