metadata
license: apache-2.0
library_name: transformers
tags:
- mergekit
- merge
base_model:
- mistralai/Mistral-Small-24B-Base-2501
- mistralai/Mistral-Small-24B-Instruct-2501
model-index:
- name: Mistral-Small-24b-Harmony
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: 16.87
name: strict accuracy
source:
url: >-
https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Mistral-Small-24b-Harmony
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: 48.42
name: normalized accuracy
source:
url: >-
https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Mistral-Small-24b-Harmony
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: 19.11
name: exact match
source:
url: >-
https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Mistral-Small-24b-Harmony
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: 17.9
name: acc_norm
source:
url: >-
https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Mistral-Small-24b-Harmony
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: 11.48
name: acc_norm
source:
url: >-
https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Mistral-Small-24b-Harmony
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: 49.23
name: accuracy
source:
url: >-
https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Mistral-Small-24b-Harmony
name: Open LLM Leaderboard
Merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merging Mistral-Small-24B Base and Instruct models together to try and create... Harmony?
Quant: https://huggingface.co./Triangle104/Mistral-Small-24b-Harmony-Q4_K_S-GGUF
Merge Method
This model was merged using the TIES merge method using mistralai/Mistral-Small-24B-Instruct-2501 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: mistralai/Mistral-Small-24B-Base-2501
parameters:
density: 1
weight: 1
- model: mistralai/Mistral-Small-24B-Instruct-2501
parameters:
density: 1
weight: 1
merge_method: ties
base_model: mistralai/Mistral-Small-24B-Instruct-2501
parameters:
normalize: false
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 27.17 |
| IFEval (0-Shot) | 16.87 |
| BBH (3-Shot) | 48.42 |
| MATH Lvl 5 (4-Shot) | 19.11 |
| GPQA (0-shot) | 17.90 |
| MuSR (0-shot) | 11.48 |
| MMLU-PRO (5-shot) | 49.23 |