Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) SOVLish-Maid-L3-8B - GGUF - Model creator: https://huggingface.co/saishf/ - Original model: https://huggingface.co/saishf/SOVLish-Maid-L3-8B/ | Name | Quant method | Size | | ---- | ---- | ---- | | [SOVLish-Maid-L3-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q2_K.gguf) | Q2_K | 2.96GB | | [SOVLish-Maid-L3-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB | | [SOVLish-Maid-L3-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.IQ3_S.gguf) | IQ3_S | 3.43GB | | [SOVLish-Maid-L3-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB | | [SOVLish-Maid-L3-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.IQ3_M.gguf) | IQ3_M | 3.52GB | | [SOVLish-Maid-L3-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q3_K.gguf) | Q3_K | 3.74GB | | [SOVLish-Maid-L3-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB | | [SOVLish-Maid-L3-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB | | [SOVLish-Maid-L3-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB | | [SOVLish-Maid-L3-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q4_0.gguf) | Q4_0 | 4.34GB | | [SOVLish-Maid-L3-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB | | [SOVLish-Maid-L3-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB | | [SOVLish-Maid-L3-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q4_K.gguf) | Q4_K | 4.58GB | | [SOVLish-Maid-L3-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB | | [SOVLish-Maid-L3-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q4_1.gguf) | Q4_1 | 4.78GB | | [SOVLish-Maid-L3-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q5_0.gguf) | Q5_0 | 5.21GB | | [SOVLish-Maid-L3-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB | | [SOVLish-Maid-L3-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q5_K.gguf) | Q5_K | 5.34GB | | [SOVLish-Maid-L3-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB | | [SOVLish-Maid-L3-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q5_1.gguf) | Q5_1 | 5.65GB | | [SOVLish-Maid-L3-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q6_K.gguf) | Q6_K | 6.14GB | | [SOVLish-Maid-L3-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVLish-Maid-L3-8B-gguf/blob/main/SOVLish-Maid-L3-8B.Q8_0.gguf) | Q8_0 | 7.95GB | Original model description: --- license: cc-by-nc-4.0 base_model: - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS - ResplendentAI/RP_Format_QuoteAsterisk_Llama3 - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS - ResplendentAI/Smarts_Llama3 - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS - ResplendentAI/Aura_Llama3 - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS - ResplendentAI/BlueMoon_Llama3 - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS - ResplendentAI/Luna_Llama3 library_name: transformers tags: - mergekit - merge --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details This is yet another experiment to see how unhinged llama3 can be. it's merged similarly to [Merge-Mayhem-L3-V2.1](https://huggingface.co/saishf/Merge-Mayhem-L3-V2.1) ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) as a base. ### Models Merged The following models were included in the merge: * [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) + [ResplendentAI/RP_Format_QuoteAsterisk_Llama3](https://huggingface.co/ResplendentAI/RP_Format_QuoteAsterisk_Llama3) * [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) + [ResplendentAI/Smarts_Llama3](https://huggingface.co/ResplendentAI/Smarts_Llama3) * [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) + [ResplendentAI/Aura_Llama3](https://huggingface.co/ResplendentAI/Aura_Llama3) * [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) + [ResplendentAI/BlueMoon_Llama3](https://huggingface.co/ResplendentAI/BlueMoon_Llama3) * [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS) + [ResplendentAI/Luna_Llama3](https://huggingface.co/ResplendentAI/Luna_Llama3) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS+ResplendentAI/Aura_Llama3 - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS+ResplendentAI/Smarts_Llama3 - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS+ResplendentAI/Luna_Llama3 - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS+ResplendentAI/BlueMoon_Llama3 - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS+ResplendentAI/RP_Format_QuoteAsterisk_Llama3 merge_method: model_stock base_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS dtype: float16 ```