Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) L3.1-Boshima-b-FIX-calc - GGUF - Model creator: https://huggingface.co/djuna/ - Original model: https://huggingface.co/djuna/L3.1-Boshima-b-FIX-calc/ | Name | Quant method | Size | | ---- | ---- | ---- | | [L3.1-Boshima-b-FIX-calc.Q2_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q2_K.gguf) | Q2_K | 2.96GB | | [L3.1-Boshima-b-FIX-calc.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.IQ3_XS.gguf) | IQ3_XS | 3.28GB | | [L3.1-Boshima-b-FIX-calc.IQ3_S.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.IQ3_S.gguf) | IQ3_S | 3.43GB | | [L3.1-Boshima-b-FIX-calc.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q3_K_S.gguf) | Q3_K_S | 3.41GB | | [L3.1-Boshima-b-FIX-calc.IQ3_M.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.IQ3_M.gguf) | IQ3_M | 3.52GB | | [L3.1-Boshima-b-FIX-calc.Q3_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q3_K.gguf) | Q3_K | 3.74GB | | [L3.1-Boshima-b-FIX-calc.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q3_K_M.gguf) | Q3_K_M | 3.74GB | | [L3.1-Boshima-b-FIX-calc.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q3_K_L.gguf) | Q3_K_L | 4.03GB | | [L3.1-Boshima-b-FIX-calc.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.IQ4_XS.gguf) | IQ4_XS | 4.18GB | | [L3.1-Boshima-b-FIX-calc.Q4_0.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q4_0.gguf) | Q4_0 | 4.34GB | | [L3.1-Boshima-b-FIX-calc.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.IQ4_NL.gguf) | IQ4_NL | 4.38GB | | [L3.1-Boshima-b-FIX-calc.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q4_K_S.gguf) | Q4_K_S | 4.37GB | | [L3.1-Boshima-b-FIX-calc.Q4_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q4_K.gguf) | Q4_K | 4.58GB | | [L3.1-Boshima-b-FIX-calc.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q4_K_M.gguf) | Q4_K_M | 4.58GB | | [L3.1-Boshima-b-FIX-calc.Q4_1.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q4_1.gguf) | Q4_1 | 4.78GB | | [L3.1-Boshima-b-FIX-calc.Q5_0.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q5_0.gguf) | Q5_0 | 5.21GB | | [L3.1-Boshima-b-FIX-calc.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q5_K_S.gguf) | Q5_K_S | 5.21GB | | [L3.1-Boshima-b-FIX-calc.Q5_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q5_K.gguf) | Q5_K | 5.34GB | | [L3.1-Boshima-b-FIX-calc.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q5_K_M.gguf) | Q5_K_M | 5.34GB | | [L3.1-Boshima-b-FIX-calc.Q5_1.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q5_1.gguf) | Q5_1 | 5.65GB | | [L3.1-Boshima-b-FIX-calc.Q6_K.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q6_K.gguf) | Q6_K | 6.14GB | | [L3.1-Boshima-b-FIX-calc.Q8_0.gguf](https://huggingface.co/RichardErkhov/djuna_-_L3.1-Boshima-b-FIX-calc-gguf/blob/main/L3.1-Boshima-b-FIX-calc.Q8_0.gguf) | Q8_0 | 7.95GB | Original model description: --- base_model: - mergekit-community/L3-Boshima-a - Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 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 ### Merge Method This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method using [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2) as a base. ### Models Merged The following models were included in the merge: * [mergekit-community/L3-Boshima-a](https://huggingface.co/mergekit-community/L3-Boshima-a) ### Configuration The following YAML configuration was used to produce this model: ```yaml merge_method: linear models: - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 parameters: weight: - filter: v_proj value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] - filter: o_proj value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] - filter: up_proj value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] - filter: gate_proj value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] - filter: down_proj value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1] - value: 1 - model: mergekit-community/L3-Boshima-a parameters: weight: - filter: v_proj value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] - filter: o_proj value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] - filter: up_proj value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] - filter: gate_proj value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] - filter: down_proj value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0] - value: 0 base_model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 tokenizer_source: base dtype: float32 out_dtype: bfloat16 ```