metadata
license: apache-2.0
library_name: transformers
tags:
- mergekit
- merge
base_model:
- NovaSky-AI/Sky-T1-mini
- Rombo-Org/Rombo-LLM-V2.5-Qwen-7b
model-index:
- name: Rombos-Novasky-7B_V1c
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: 40.8
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Rombos-Novasky-7B_V1c
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: 20.42
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Rombos-Novasky-7B_V1c
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: 8.53
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Rombos-Novasky-7B_V1c
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: 6.15
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Rombos-Novasky-7B_V1c
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: 14.04
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Rombos-Novasky-7B_V1c
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: 19.31
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Rombos-Novasky-7B_V1c
name: Open LLM Leaderboard
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Third attempt. Hopefully this goes better...
Quants:
https://huggingface.co/Triangle104/Rombos-Novasky-7B_V1c-Q4_K_M-GGUF
https://huggingface.co/mradermacher/Rombos-Novasky-7B_V1c-GGUF
Merge Method
This model was merged using the TIES merge method using Rombo-Org/Rombo-LLM-V2.5-Qwen-7b 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: Rombo-Org/Rombo-LLM-V2.5-Qwen-7b
parameters:
density: 0.6
weight: 0.6
- model: NovaSky-AI/Sky-T1-mini
parameters:
density: 0.4
weight: 0.4
merge_method: ties
base_model: Rombo-Org/Rombo-LLM-V2.5-Qwen-7b
parameters:
normalize: false
int8_mask: true
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 18.21 |
| IFEval (0-Shot) | 40.80 |
| BBH (3-Shot) | 20.42 |
| MATH Lvl 5 (4-Shot) | 8.53 |
| GPQA (0-shot) | 6.15 |
| MuSR (0-shot) | 14.04 |
| MMLU-PRO (5-shot) | 19.31 |