150 lines
3.9 KiB
Markdown
150 lines
3.9 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: apache-2.0
|
|
library_name: transformers
|
|
tags:
|
|
- unsloth
|
|
- trl
|
|
- sft
|
|
- theprint
|
|
- ReWiz
|
|
base_model:
|
|
- unsloth/Llama-3.2-3B-Instruct
|
|
datasets:
|
|
- KingNish/reasoning-base-20k
|
|
- arcee-ai/EvolKit-20k
|
|
- cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered
|
|
pipeline_tag: text-generation
|
|
model-index:
|
|
- name: ReWiz-Llama-3.2-3B
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: IFEval (0-Shot)
|
|
type: HuggingFaceH4/ifeval
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: inst_level_strict_acc and prompt_level_strict_acc
|
|
value: 46.49
|
|
name: strict accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Llama-3.2-3B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: BBH (3-Shot)
|
|
type: BBH
|
|
args:
|
|
num_few_shot: 3
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 19.29
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Llama-3.2-3B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MATH Lvl 5 (4-Shot)
|
|
type: hendrycks/competition_math
|
|
args:
|
|
num_few_shot: 4
|
|
metrics:
|
|
- type: exact_match
|
|
value: 9.74
|
|
name: exact match
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Llama-3.2-3B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: GPQA (0-shot)
|
|
type: Idavidrein/gpqa
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 4.47
|
|
name: acc_norm
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Llama-3.2-3B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MuSR (0-shot)
|
|
type: TAUR-Lab/MuSR
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 6.94
|
|
name: acc_norm
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Llama-3.2-3B
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MMLU-PRO (5-shot)
|
|
type: TIGER-Lab/MMLU-Pro
|
|
config: main
|
|
split: test
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 20.97
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Llama-3.2-3B
|
|
name: Open LLM Leaderboard
|
|
---
|
|
<img src="https://huggingface.co/theprint/ReWiz-Llama-3.2-3B/resolve/main/ReWiz_banner.png">
|
|
|
|
# Model Card for Model ID
|
|
|
|
<!-- Provide a quick summary of what the model is/does. -->
|
|
|
|
|
|
|
|
## Model Details
|
|
|
|
### Model Description
|
|
|
|
<!-- Provide a longer summary of what this model is. -->
|
|
|
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
|
|
|
- **Developed by:** theprint/Rasmus Rasmussen
|
|
- **Funded by [optional]:** No one
|
|
- **Shared by [optional]:** You?
|
|
|
|
|
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_theprint__ReWiz-Llama-3.2-3B)
|
|
|
|
| Metric |Value|
|
|
|-------------------|----:|
|
|
|Avg. |17.98|
|
|
|IFEval (0-Shot) |46.49|
|
|
|BBH (3-Shot) |19.29|
|
|
|MATH Lvl 5 (4-Shot)| 9.74|
|
|
|GPQA (0-shot) | 4.47|
|
|
|MuSR (0-shot) | 6.94|
|
|
|MMLU-PRO (5-shot) |20.97|
|
|
|