--- license: apache-2.0 library_name: transformers tags: - mergekit - merge base_model: - Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 - kloodia/lora-8b-bio - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 - Blackroot/Llama-3-8B-Abomination-LORA - Sao10K/L3-8B-Stheno-v3.2 - grimjim/Llama-3-Instruct-abliteration-LoRA-8B - arcee-ai/Llama-3.1-SuperNova-Lite - grimjim/Llama-3-Instruct-abliteration-LoRA-8B - mlabonne/Hermes-3-Llama-3.1-8B-lorablated - kloodia/lora-8b-physic - aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored - kloodia/lora-8b-medic model-index: - name: Aspire-8B-model_stock 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: 71.41 name: strict accuracy source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-8B-model_stock 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: 32.53 name: normalized accuracy source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-8B-model_stock 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: 12.99 name: exact match source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-8B-model_stock 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: 8.61 name: acc_norm source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-8B-model_stock 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: 13.46 name: acc_norm source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-8B-model_stock 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: 30.7 name: accuracy source: url: https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Aspire-8B-model_stock 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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co./Sao10K/L3-8B-Stheno-v3.2) + [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co./grimjim/Llama-3-Instruct-abliteration-LoRA-8B) as a base. ### Models Merged The following models were included in the merge: * [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co./Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2) + [kloodia/lora-8b-bio](https://huggingface.co./kloodia/lora-8b-bio) * [ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1](https://huggingface.co./ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1) + [Blackroot/Llama-3-8B-Abomination-LORA](https://huggingface.co./Blackroot/Llama-3-8B-Abomination-LORA) * [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co./arcee-ai/Llama-3.1-SuperNova-Lite) + [grimjim/Llama-3-Instruct-abliteration-LoRA-8B](https://huggingface.co./grimjim/Llama-3-Instruct-abliteration-LoRA-8B) * [mlabonne/Hermes-3-Llama-3.1-8B-lorablated](https://huggingface.co./mlabonne/Hermes-3-Llama-3.1-8B-lorablated) + [kloodia/lora-8b-physic](https://huggingface.co./kloodia/lora-8b-physic) * [aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored](https://huggingface.co./aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored) + [kloodia/lora-8b-medic](https://huggingface.co./kloodia/lora-8b-medic) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2+kloodia/lora-8b-bio - model: arcee-ai/Llama-3.1-SuperNova-Lite+grimjim/Llama-3-Instruct-abliteration-LoRA-8B - model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated+kloodia/lora-8b-physic - model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored+kloodia/lora-8b-medic - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1+Blackroot/Llama-3-8B-Abomination-LORA merge_method: model_stock base_model: Sao10K/L3-8B-Stheno-v3.2+grimjim/Llama-3-Instruct-abliteration-LoRA-8B normalize: false int8_mask: true dtype: bfloat16 ``` ![image.png](https://cdn-uploads.huggingface.co/production/uploads/632149f88c0da827c72dccde/IkTIiq6HjCkaJefSNtGLD.png) # [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/details_DreadPoor__Aspire-8B-model_stock) | Metric |Value| |-------------------|----:| |Avg. |28.28| |IFEval (0-Shot) |71.41| |BBH (3-Shot) |32.53| |MATH Lvl 5 (4-Shot)|12.99| |GPQA (0-shot) | 8.61| |MuSR (0-shot) |13.46| |MMLU-PRO (5-shot) |30.70|