metadata
tags:
- mergekit
- merge
base_model:
- teknium/OpenHermes-2.5-Mistral-7B
- nlpguy/Hermes-low-tune-2
- charlesdedampierre/TopicNeuralHermes-2.5-Mistral-7B
- openaccess-ai-collective/openhermes-2_5-dpo-no-robots
- flemmingmiguel/Mistrality-7B
- beowolx/MistralHermes-CodePro-7B-v1
license_name: apache-2.0-mit-dual-license
license_link: https://huggingface.co/nlpguy/Hermes-low-tune-3.1/raw/main/LICENSE
model-index:
- name: Hermes-low-tune-3.1
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: 65.44
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
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: 84.6
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
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: 64.13
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
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: 53.59
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
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: 78.61
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
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: 63.46
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-3.1
name: Open LLM Leaderboard
merged
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the task arithmetic merge method using teknium/OpenHermes-2.5-Mistral-7B as a base.
Models Merged
The following models were included in the merge:
- nlpguy/Hermes-low-tune-2
- charlesdedampierre/TopicNeuralHermes-2.5-Mistral-7B
- openaccess-ai-collective/openhermes-2_5-dpo-no-robots
- flemmingmiguel/Mistrality-7B
- beowolx/MistralHermes-CodePro-7B-v1
Configuration
The following YAML configuration was used to produce this model:
base_model: teknium/OpenHermes-2.5-Mistral-7B
dtype: bfloat16
merge_method: task_arithmetic
slices:
- sources:
- layer_range: [0, 32]
model: teknium/OpenHermes-2.5-Mistral-7B
- layer_range: [0, 32]
model: nlpguy/Hermes-low-tune-2
parameters:
weight: 0.2
- layer_range: [0, 32]
model: beowolx/MistralHermes-CodePro-7B-v1
parameters:
weight: 0.2
- layer_range: [0, 32]
model: flemmingmiguel/Mistrality-7B
parameters:
weight: 0.2
- layer_range: [0, 32]
model: charlesdedampierre/TopicNeuralHermes-2.5-Mistral-7B
parameters:
weight: 0.2
- layer_range: [0, 32]
model: openaccess-ai-collective/openhermes-2_5-dpo-no-robots
parameters:
weight: 0.2
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 68.31 |
AI2 Reasoning Challenge (25-Shot) | 65.44 |
HellaSwag (10-Shot) | 84.60 |
MMLU (5-Shot) | 64.13 |
TruthfulQA (0-shot) | 53.59 |
Winogrande (5-shot) | 78.61 |
GSM8k (5-shot) | 63.46 |