metadata
license: mit
tags:
- moe
- DPO
- RL-TUNED
model-index:
- name: Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
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: 74.91
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
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: 89.3
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
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: 64.67
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
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: 78.02
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
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: 88.24
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
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: 69.52
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
name: Open LLM Leaderboard
- DPO Trainer with dataset jondurbin/truthy-dpo-v0.1 to improve [TomGrc/FusionNet_7Bx2_MoE_14B]
DPO Trainer TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_yunconglong__Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |77.44|
|AI2 Reasoning Challenge (25-Shot)|74.91|
|HellaSwag (10-Shot) |89.30|
|MMLU (5-Shot) |64.67|
|TruthfulQA (0-shot) |78.02|
|Winogrande (5-shot) |88.24|
|GSM8k (5-shot) |69.52|