metadata
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/zephyr-sft-bnb-4bit
model-index:
- name: ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205
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: 31.99
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205
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: 16.71
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205
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: 0.15
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205
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: 3.47
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205
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: 12.1
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205
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: 12.49
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sonthenguyen/ft-unsloth-zephyr-sft-bnb-4bit-20241014-164205
name: Open LLM Leaderboard
Uploaded model
- Developed by: sonthenguyen
- License: apache-2.0
- Finetuned from model : unsloth/zephyr-sft-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 12.82 |
IFEval (0-Shot) | 31.99 |
BBH (3-Shot) | 16.71 |
MATH Lvl 5 (4-Shot) | 0.15 |
GPQA (0-shot) | 3.47 |
MuSR (0-shot) | 12.10 |
MMLU-PRO (5-shot) | 12.49 |