Hugging Face's logo

NLPinas
/
yi-bagel-2x34b

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files
yi-bagel-2x34b / README.md
jaspercatapang's picture
jaspercatapang
Update README.md
924e54b verified
preview code
|
raw
history blame
2.94 kB
metadata
base_model:
  - jondurbin/bagel-dpo-34b-v0.2
  - jondurbin/nontoxic-bagel-34b-v0.2
tags:
  - mergekit
  - merge
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE

yi-bagel-2x34b

Released January 11, 2024

bagel-burger

This is a merge of pre-trained language models created using mergekit. For more information, kindly refer to the model cards from jondurbin linked in the section below. This model debuted in the leaderboard at rank #4 (January 11, 2024).

Merge Details

Merge Method

This model is an expertimental merge using the linear merge method. This is to assess the degree of which the DPO has an effect, in terms of censoring, as used in jondurbin/bagel-dpo-34b-v0.2.

Models Merged

The following models were included in the merge:

Open LLM Leaderboard Metrics (as of January 11, 2024)

Metric Value
MMLU (5-shot) 76.60
ARC (25-shot) 72.70
HellaSwag (10-shot) 85.44
TruthfulQA (0-shot) 71.42
Winogrande (5-shot) 82.72
GSM8K (5-shot) 60.73
Average 74.93

According to the leaderboard description, here are the benchmarks used for the evaluation:

  • MMLU (5-shot) - a test to measure a text model’s multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more.
  • AI2 Reasoning Challenge -ARC- (25-shot) - a set of grade-school science questions.
  • HellaSwag (10-shot) - a test of commonsense inference, which is easy for humans (~95%) but challenging for SOTA models.
  • TruthfulQA (0-shot) - a test to measure a model’s propensity to reproduce falsehoods commonly found online.
  • Winogrande (5-shot) - an adversarial and difficult Winograd benchmark at scale, for commonsense reasoning.
  • GSM8k (5-shot) - diverse grade school math word problems to measure a model's ability to solve multi-step mathematical reasoning problems.

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: jondurbin/nontoxic-bagel-34b-v0.2
    parameters:
      weight: 0.5
  - model: jondurbin/bagel-dpo-34b-v0.2
    parameters:
      weight: 0.5
merge_method: linear
dtype: float16