Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) LogoS-7Bx2-MoE-13B-v0.2 - GGUF - Model creator: https://huggingface.co/RubielLabarta/ - Original model: https://huggingface.co/RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2/ | Name | Quant method | Size | | ---- | ---- | ---- | | [LogoS-7Bx2-MoE-13B-v0.2.Q2_K.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q2_K.gguf) | Q2_K | 4.43GB | | [LogoS-7Bx2-MoE-13B-v0.2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.IQ3_XS.gguf) | IQ3_XS | 4.94GB | | [LogoS-7Bx2-MoE-13B-v0.2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.IQ3_S.gguf) | IQ3_S | 5.22GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q3_K_S.gguf) | Q3_K_S | 5.2GB | | [LogoS-7Bx2-MoE-13B-v0.2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.IQ3_M.gguf) | IQ3_M | 5.34GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q3_K.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q3_K.gguf) | Q3_K | 5.78GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q3_K_M.gguf) | Q3_K_M | 5.78GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q3_K_L.gguf) | Q3_K_L | 6.27GB | | [LogoS-7Bx2-MoE-13B-v0.2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.IQ4_XS.gguf) | IQ4_XS | 6.5GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q4_0.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q4_0.gguf) | Q4_0 | 6.78GB | | [LogoS-7Bx2-MoE-13B-v0.2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.IQ4_NL.gguf) | IQ4_NL | 6.85GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q4_K_S.gguf) | Q4_K_S | 6.84GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q4_K.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q4_K.gguf) | Q4_K | 7.25GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q4_K_M.gguf) | Q4_K_M | 7.25GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q4_1.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q4_1.gguf) | Q4_1 | 7.52GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q5_0.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q5_0.gguf) | Q5_0 | 8.26GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q5_K_S.gguf) | Q5_K_S | 8.26GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q5_K.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q5_K.gguf) | Q5_K | 8.51GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q5_K_M.gguf) | Q5_K_M | 8.51GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q5_1.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q5_1.gguf) | Q5_1 | 9.01GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q6_K.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q6_K.gguf) | Q6_K | 9.84GB | | [LogoS-7Bx2-MoE-13B-v0.2.Q8_0.gguf](https://huggingface.co/RichardErkhov/RubielLabarta_-_LogoS-7Bx2-MoE-13B-v0.2-gguf/blob/main/LogoS-7Bx2-MoE-13B-v0.2.Q8_0.gguf) | Q8_0 | 12.75GB | Original model description: --- language: - en - es license: apache-2.0 tags: - moe - merge base_model: - yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B - TomGrc/FusionNet_7Bx2_MoE_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: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 74.49 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_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: num_few_shot: 10 metrics: - type: acc_norm value: 89.07 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_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: num_few_shot: 5 metrics: - type: acc value: 64.74 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?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: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 74.57 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?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: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 88.32 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?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: num_few_shot: 5 metrics: - type: acc value: 71.65 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?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](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_RubielLabarta__LogoS-7Bx2-MoE-13B-v0.1) | Metric |Value| |---------------------------------|----:| |Avg. |77.14| |AI2 Reasoning Challenge (25-Shot)|74.49| |HellaSwag (10-Shot) |89.07| |MMLU (5-Shot) |64.74| |TruthfulQA (0-shot) |74.57| |Winogrande (5-shot) |88.32| |GSM8k (5-shot) |71.65|