|
--- |
|
license: apache-2.0 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
base_model: |
|
- bamec66557/VICIOUS_MESH-12B-BETA |
|
- bamec66557/VICIOUS_MESH-12B-OMEGA |
|
model-index: |
|
- name: Mistral-Nemo-VICIOUS_MESH-12B-2407 |
|
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: 67.21 |
|
name: strict accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407 |
|
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: 31.36 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407 |
|
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: 12.08 |
|
name: exact match |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407 |
|
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: 8.84 |
|
name: acc_norm |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407 |
|
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: 14.34 |
|
name: acc_norm |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407 |
|
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: 29.76 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/Mistral-Nemo-VICIOUS_MESH-12B-2407 |
|
name: Open LLM Leaderboard |
|
--- |
|
# merge |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the SLERP merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [bamec66557/VICIOUS_MESH-12B-BETA](https://huggingface.co/bamec66557/VICIOUS_MESH-12B-BETA) |
|
* [bamec66557/VICIOUS_MESH-12B-OMEGA](https://huggingface.co/bamec66557/VICIOUS_MESH-12B-OMEGA) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
base_model: bamec66557/VICIOUS_MESH-12B-OMEGA |
|
dtype: bfloat16 |
|
merge_method: slerp |
|
tokenizer_source: base |
|
|
|
# Slices Configuration |
|
slices: |
|
- sources: |
|
- model: bamec66557/VICIOUS_MESH-12B-OMEGA |
|
layer_range: [0, 10] |
|
- model: bamec66557/VICIOUS_MESH-12B-BETA |
|
layer_range: [0, 10] |
|
parameters: |
|
t: |
|
- name: self_attn |
|
value: [0.5, 0.55, 0.6, 0.65, 0.7] |
|
- name: mlp |
|
value: [1.0, 1.05, 1.1, 1.15, 1.2] |
|
- name: layer_norm |
|
value: [0.9, 0.95, 1.0, 1.05, 1.1] |
|
|
|
- sources: |
|
- model: bamec66557/VICIOUS_MESH-12B-OMEGA |
|
layer_range: [10, 20] |
|
- model: bamec66557/VICIOUS_MESH-12B-BETA |
|
layer_range: [10, 20] |
|
parameters: |
|
t: |
|
- name: self_attn |
|
value: [0.4, 0.45, 0.5, 0.55, 0.6] |
|
- name: mlp |
|
value: [1.1, 1.15, 1.2, 1.25, 1.3] |
|
- name: layer_norm |
|
value: [1.0, 1.05, 1.1, 1.15, 1.2] |
|
|
|
- sources: |
|
- model: bamec66557/VICIOUS_MESH-12B-OMEGA |
|
layer_range: [20, 30] |
|
- model: bamec66557/VICIOUS_MESH-12B-BETA |
|
layer_range: [20, 30] |
|
parameters: |
|
t: |
|
- name: self_attn |
|
value: [0.6, 0.65, 0.7, 0.75, 0.8] |
|
- name: mlp |
|
value: [0.9, 0.95, 1.0, 1.05, 1.1] |
|
- name: layer_norm |
|
value: [0.85, 0.9, 0.95, 1.0, 1.05] |
|
|
|
- sources: |
|
- model: bamec66557/VICIOUS_MESH-12B-OMEGA |
|
layer_range: [30, 40] |
|
- model: bamec66557/VICIOUS_MESH-12B-BETA |
|
layer_range: [30, 40] |
|
parameters: |
|
t: |
|
- name: self_attn |
|
value: [0.7, 0.75, 0.8, 0.85, 0.9] |
|
- name: mlp |
|
value: [0.8, 0.85, 0.9, 0.95, 1.0] |
|
- name: layer_norm |
|
value: [0.8, 0.85, 0.9, 0.95, 1.0] |
|
|
|
# Regularization |
|
regularization: |
|
- method: gradient_penalty |
|
scale: 0.05 # Increased influence for gradient control |
|
- method: weight_clipping |
|
clip_range: [-0.2, 0.2] # Broader clipping range for flexibility |
|
- method: random_noise |
|
scale: 0.01 # Stronger noise injection |
|
- method: attention_dropout |
|
scale: 0.1 # Higher dropout to reduce attention fixation |
|
|
|
# Postprocessing |
|
postprocessing: |
|
- operation: entropy_regularization |
|
scale: 0.05 # Stronger encouragement for diverse outputs |
|
- operation: non_linear_scaling |
|
parameters: |
|
function: tanh |
|
- operation: sharpening |
|
intensity: 0.5 # Enhanced sharpening for precise outputs |
|
- operation: gaussian_smoothing |
|
sigma: 1.5 # Increased smoothing for stable outputs |
|
- operation: normalize |
|
- operation: dynamic_scaling |
|
scale_range: [0.8, 1.2] # Expanded dynamic range for scaling |
|
- operation: smoothing |
|
parameters: |
|
adaptive: true |
|
range: [0.85, 1.15] # Wider adaptive smoothing range |
|
kernel_size: 5 |
|
|
|
``` |
|
# [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/bamec66557__Mistral-Nemo-VICIOUS_MESH-12B-2407-details) |
|
|
|
| Metric |Value| |
|
|-------------------|----:| |
|
|Avg. |27.26| |
|
|IFEval (0-Shot) |67.21| |
|
|BBH (3-Shot) |31.36| |
|
|MATH Lvl 5 (4-Shot)|12.08| |
|
|GPQA (0-shot) | 8.84| |
|
|MuSR (0-shot) |14.34| |
|
|MMLU-PRO (5-shot) |29.76| |
|
|
|
|
