|
--- |
|
language: |
|
- en |
|
license: other |
|
tags: |
|
- chatml |
|
base_model: google/gemma-2b |
|
datasets: |
|
- HuggingFaceH4/ultrachat_200k |
|
- teknium/OpenHermes-2.5 |
|
- meta-math/MetaMathQA |
|
- LDJnr/Capybara |
|
- glaiveai/glaive-code-assistant-v2 |
|
- migtissera/Tess-Coder-v1.0 |
|
- m-a-p/Code-Feedback |
|
- ise-uiuc/Magicoder-Evol-Instruct-110K |
|
- ise-uiuc/Magicoder-OSS-Instruct-75K |
|
license_name: gemma-terms-of-use |
|
license_link: https://ai.google.dev/gemma/terms |
|
model-index: |
|
- name: new_model_test |
|
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: 52.56 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=pansophic/new_model_test |
|
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: 73.65 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=pansophic/new_model_test |
|
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: 46.02 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=pansophic/new_model_test |
|
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: 51.25 |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=pansophic/new_model_test |
|
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: 66.38 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=pansophic/new_model_test |
|
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: 37.91 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=pansophic/new_model_test |
|
name: Open LLM Leaderboard |
|
--- |
|
|
|
|
|
This is just a preview model. It is a finetuned gemma-2b with added chatml tokens. |
|
|
|
# [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_pansophic__new_model_test) |
|
|
|
| Metric |Value| |
|
|---------------------------------|----:| |
|
|Avg. |54.63| |
|
|AI2 Reasoning Challenge (25-Shot)|52.56| |
|
|HellaSwag (10-Shot) |73.65| |
|
|MMLU (5-Shot) |46.02| |
|
|TruthfulQA (0-shot) |51.25| |
|
|Winogrande (5-shot) |66.38| |
|
|GSM8k (5-shot) |37.91| |
|
|
|
|
