SnowStorm-v1.15-4x8B-A
Collection
v1.15A, vision, based on LumiMaidOAS
•
3 items
•
Updated
Experimental RP-oriented MoE, the idea was to get a model that would be equal to or better than Mixtral 8x7B and it's finetunes in RP/ERP tasks.
There's:
Llama 3 SnowStorm v1.15A 4x8B
base_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
gate_mode: random
dtype: bfloat16
experts_per_token: 2
experts:
- source_model: Nitral-AI_Poppy_Porpoise-1.0-L3-8B
- source_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
- source_model: openlynn_Llama-3-Soliloquy-8B-v2
- source_model: Sao10K_L3-8B-Stheno-v3.1
Models used
- Nitral-AI/Poppy_Porpoise-1.0-L3-8B
- NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
- openlynn/Llama-3-Soliloquy-8B-v2
- Sao10K/L3-8B-Stheno-v3.1
Difference(from SnowStorm v1.0)
Vision
Prompt format: Llama 3
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.68 |
| AI2 Reasoning Challenge (25-Shot) | 62.20 |
| HellaSwag (10-Shot) | 81.09 |
| MMLU (5-Shot) | 67.89 |
| TruthfulQA (0-shot) | 52.11 |
| Winogrande (5-shot) | 76.32 |
| GSM8k (5-shot) | 66.49 |
- Downloads last month
- 2
Model tree for xxx777xxxASD/L3-SnowStorm-v1.15-4x8B-A
Collection including xxx777xxxASD/L3-SnowStorm-v1.15-4x8B-A
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard62.200
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard81.090
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard67.890
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard52.110
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard76.320
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard66.490