Made by Liminerity <#
INEX4-7b
INEX4-7b is a merge of the following models using mergekit:
🧩 Configuration
slices:
- sources:
- model: liminerity/Ingot-7b-slerp-7-forged
layer_range: [0, 32]
- model: yam-peleg/Experiment26-7B
layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/Ingot-7b-slerp-7-forged
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
model: liminerity/merge
slices:
- sources:
- model: liminerity/Ingot-7b-slerp-7-forged
layer_range: [0, 32]
- model: liminerity/merge
layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/Ingot-7b-slerp-7-forged
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
model: liminerity/merge1
slices:
- sources:
- model: yam-peleg/Experiment26-7B
layer_range: [0, 32]
- model: liminerity/merge1
layer_range: [0, 32]
merge_method: slerp
base_model: yam-peleg/Experiment26-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: float16
model: liminerity/merge2
slices:
- sources:
- model: liminerity/merge2
layer_range: [0, 32]
- model: liminerity/merge1
layer_range: [0, 32]
merge_method: slerp
base_model: liminerity/merge2
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
model: INEX-7b
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 75.84 |
AI2 Reasoning Challenge (25-Shot) | 72.95 |
HellaSwag (10-Shot) | 88.79 |
MMLU (5-Shot) | 64.70 |
TruthfulQA (0-shot) | 74.42 |
Winogrande (5-shot) | 83.90 |
GSM8k (5-shot) | 70.28 |
- Downloads last month
- 18
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for MSL7/INEX4-7b
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard72.950
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard88.790
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.700
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard74.420
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard83.900
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard70.280