LiteLlama-460M-1T / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
b1575e3 verified
metadata
language:
  - en
license: mit
tags:
  - llama2
  - llama-2
  - llama
  - llama2 architecture
  - litellama
datasets:
  - Redpajama
metrics:
  - MMLU
widget:
  - text: 'Q: What is the largest bird?\nA:'
model-index:
  - name: LiteLlama-460M-1T
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 24.83
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 38.39
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 25.96
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 41.59
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 50.2
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 0
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ahxt/LiteLlama-460M-1T
          name: Open LLM Leaderboard

LiteLlama: Reduced-Scale Llama

We present an open-source reproduction of Meta AI's LLaMa 2. However, with significantly reduced model sizes, LiteLlama-460M-1T has 460M parameters trained with 1T tokens.

Dataset and Tokenization

We train our models on part of RedPajama dataset. We use the GPT2Tokenizer to tokenize the text.

Training Details

The model was trained with ~1T tokens (0.98T). num of tokens = stepslengthbatch_size=4996791024192=98240888832≈0.98T.

The training curve is at this WandB project.

Using with HuggingFace Transformers

The experimental checkpoints can be directly loaded by Transformers library. The following code snippet shows how to load the our experimental model and generate text with it.

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_path = 'ahxt/LiteLlama-460M-1T'

model = AutoModelForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
model.eval()

prompt = 'Q: What is the largest bird?\nA:'
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
tokens = model.generate(input_ids, max_length=20)
print( tokenizer.decode(tokens[0].tolist(), skip_special_tokens=True) )
# Q: What is the largest bird?\nA: The largest bird is a black-headed gull.

Evaluation

We evaluate our models on the MMLU task.

Models #parameters zero-shot 5-shot
llama 7B 28.46 35.05
openllama 3B 24.90 26.71
TinyLlama-1.1B-step-50K-105b 1.1B 19.00 26.53
LiteLlama-460M-1T 0.46B 21.13 26.39

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 26.65
ARC (25-shot) 24.91
HellaSwag (10-shot) 38.47
MMLU (5-shot) 26.17
TruthfulQA (0-shot) 41.59
Winogrande (5-shot) 49.88
GSM8K (5-shot) 0.0
DROP (3-shot) 5.51

Contact

This model was developed by Xiaotian Han from Texas A&M University at the DATA Lab under the supervision of Prof. Xia "Ben" Hu, and the model is released under MIT License.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 30.16
AI2 Reasoning Challenge (25-Shot) 24.83
HellaSwag (10-Shot) 38.39
MMLU (5-Shot) 25.96
TruthfulQA (0-shot) 41.59
Winogrande (5-shot) 50.20
GSM8k (5-shot) 0.00