RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LogoS-7Bx2-MoE-13B-v0.2 - bnb 4bits

• —Model creator: https://huggingface.co/RubielLabarta/
• —Original model: https://huggingface.co/RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2/

Original model description: --- language:

• —en
• —es license: apache-2.0 tags:
• —moe
• —merge base_model:
• —yunconglong/TruthfulDPOTomGrcFusionNet7Bx2MoE13B
• —TomGrc/FusionNet7Bx2MoE_14B model-index:
• —name: LogoS-7Bx2-MoE-13B-v0.1 results:
• —task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2arc config: ARC-Challenge split: test args: numfew_shot: 25 metrics:
• —type: accnorm value: 74.49 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=RubielLabarta/LogoS-7Bx2-MoE-13B-v0.1 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: numfewshot: 10 metrics:
• —type: accnorm value: 89.07 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllm_leaderboard?query=RubielLabarta/LogoS-7Bx2-MoE-13B-v0.1 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: numfewshot: 5 metrics:
• —type: acc value: 64.74 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=RubielLabarta/LogoS-7Bx2-MoE-13B-v0.1 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthfulqa config: multiplechoice split: validation args: numfewshot: 0 metrics:
• —type: mc2 value: 74.57 source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=RubielLabarta/LogoS-7Bx2-MoE-13B-v0.1 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winograndexl split: validation args: numfew_shot: 5 metrics:
• —type: acc value: 88.32 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=RubielLabarta/LogoS-7Bx2-MoE-13B-v0.1 name: Open LLM Leaderboard
• —task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: numfewshot: 5 metrics:
• —type: acc value: 71.65 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/openllmleaderboard?query=RubielLabarta/LogoS-7Bx2-MoE-13B-v0.1 name: Open LLM Leaderboard ---

LogoS-7Bx2-MoE-13B-v0.1

Model built by @RubielLabarta using SLERP merge method. The model is release for research purposes only, commercial use is not allowed.

The LogoS is a model to experiment with the MoE method, which could significantly increase the performance of the original model. The model has 12.9B parameters.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here