--- base_model: - Hjgugugjhuhjggg/mergekit-ties-qgcitfu - ValiantLabs/Llama3.2-3B-ShiningValiant2 - CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct - Atharva26/llama-3.2-3b-mathdaily-chatbot - bunnycore/Llama-3.2-3B-ProdigyPlusPlus - disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot - Hjgugugjhuhjggg/mergekit-ties-poovzrh - bunnycore/Llama-3.2-3B-Long-Think - noaebbot/llama3.2-3B-insights - ValiantLabs/Llama3.2-3B-Enigma - huihui-ai/Llama-3.2-3B-Instruct-abliterated - meta-llama/Llama-3.2-3B-Instruct - Hjgugugjhuhjggg/mergekit-ties-pghuyfi - Diluksha/Llama_3.2_3B_sql_finetuned_full - bunnycore/Llama-3.2-3B-Mix - Hjgugugjhuhjggg/mergekit-ties-xflmond - bunnycore/Llama-3.2-3B-Pure-RP - chuanli11/Llama-3.2-3B-Instruct-uncensored - EmTpro01/llama-3.2-Code-Generator - bunnycore/Llama-3.2-3B-Booval - bunnycore/Llama-3.2-3B-Prodigy - BrainWave-ML/llama3.2-3B-codemath-orpo - bunnycore/Llama-3.2-3B-TitanFusion - bunnycore/Llama-3.2-3B-CodeReactor - Hjgugugjhuhjggg/mergekit-ties-kmlzhzo - Hjgugugjhuhjggg/mergekit-ties-esawwda - bunnycore/Llama-3.2-3B-TitanFusion-v2 - disi-unibo-nlp/llama3.2-3B-SFT-medmcqa-triples-cot - bunnycore/Llama-3.2-3B-Mix-Skill - bunnycore/Llama-3.2-3B-Sci-Think - AELLM/Llama-3.2-Chibi-3B - AcademieDuNumerique/Llama-3.2-3B-SQL-Instruct - roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA - Hjgugugjhuhjggg/mergekit-ties-dkhnzcn - Isotonic/reasoning-llama3.2-3b - meta-llama/Llama-3.2-3B - bunnycore/Llama-3.2-3B-Apex - TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient - CK0607/llama3.2-3B-CodeP - bunnycore/Llama-3.2-3B-Stock 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 [huihui-ai/Llama-3.2-3B-Instruct-abliterated](https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated) as a base. ### Models Merged The following models were included in the merge: * [Hjgugugjhuhjggg/mergekit-ties-qgcitfu](https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-qgcitfu) * [ValiantLabs/Llama3.2-3B-ShiningValiant2](https://huggingface.co/ValiantLabs/Llama3.2-3B-ShiningValiant2) * [CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct](https://huggingface.co/CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct) * [Atharva26/llama-3.2-3b-mathdaily-chatbot](https://huggingface.co/Atharva26/llama-3.2-3b-mathdaily-chatbot) * [bunnycore/Llama-3.2-3B-ProdigyPlusPlus](https://huggingface.co/bunnycore/Llama-3.2-3B-ProdigyPlusPlus) * [disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot](https://huggingface.co/disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot) * [Hjgugugjhuhjggg/mergekit-ties-poovzrh](https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-poovzrh) * [bunnycore/Llama-3.2-3B-Long-Think](https://huggingface.co/bunnycore/Llama-3.2-3B-Long-Think) * [noaebbot/llama3.2-3B-insights](https://huggingface.co/noaebbot/llama3.2-3B-insights) * [ValiantLabs/Llama3.2-3B-Enigma](https://huggingface.co/ValiantLabs/Llama3.2-3B-Enigma) * [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) * [Hjgugugjhuhjggg/mergekit-ties-pghuyfi](https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-pghuyfi) * [Diluksha/Llama_3.2_3B_sql_finetuned_full](https://huggingface.co/Diluksha/Llama_3.2_3B_sql_finetuned_full) * [bunnycore/Llama-3.2-3B-Mix](https://huggingface.co/bunnycore/Llama-3.2-3B-Mix) * [Hjgugugjhuhjggg/mergekit-ties-xflmond](https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-xflmond) * [bunnycore/Llama-3.2-3B-Pure-RP](https://huggingface.co/bunnycore/Llama-3.2-3B-Pure-RP) * [chuanli11/Llama-3.2-3B-Instruct-uncensored](https://huggingface.co/chuanli11/Llama-3.2-3B-Instruct-uncensored) * [EmTpro01/llama-3.2-Code-Generator](https://huggingface.co/EmTpro01/llama-3.2-Code-Generator) * [bunnycore/Llama-3.2-3B-Booval](https://huggingface.co/bunnycore/Llama-3.2-3B-Booval) * [bunnycore/Llama-3.2-3B-Prodigy](https://huggingface.co/bunnycore/Llama-3.2-3B-Prodigy) * [BrainWave-ML/llama3.2-3B-codemath-orpo](https://huggingface.co/BrainWave-ML/llama3.2-3B-codemath-orpo) * [bunnycore/Llama-3.2-3B-TitanFusion](https://huggingface.co/bunnycore/Llama-3.2-3B-TitanFusion) * [bunnycore/Llama-3.2-3B-CodeReactor](https://huggingface.co/bunnycore/Llama-3.2-3B-CodeReactor) * [Hjgugugjhuhjggg/mergekit-ties-kmlzhzo](https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-kmlzhzo) * [Hjgugugjhuhjggg/mergekit-ties-esawwda](https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-esawwda) * [bunnycore/Llama-3.2-3B-TitanFusion-v2](https://huggingface.co/bunnycore/Llama-3.2-3B-TitanFusion-v2) * [disi-unibo-nlp/llama3.2-3B-SFT-medmcqa-triples-cot](https://huggingface.co/disi-unibo-nlp/llama3.2-3B-SFT-medmcqa-triples-cot) * [bunnycore/Llama-3.2-3B-Mix-Skill](https://huggingface.co/bunnycore/Llama-3.2-3B-Mix-Skill) * [bunnycore/Llama-3.2-3B-Sci-Think](https://huggingface.co/bunnycore/Llama-3.2-3B-Sci-Think) * [AELLM/Llama-3.2-Chibi-3B](https://huggingface.co/AELLM/Llama-3.2-Chibi-3B) * [AcademieDuNumerique/Llama-3.2-3B-SQL-Instruct](https://huggingface.co/AcademieDuNumerique/Llama-3.2-3B-SQL-Instruct) * [roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA](https://huggingface.co/roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA) * [Hjgugugjhuhjggg/mergekit-ties-dkhnzcn](https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-dkhnzcn) * [Isotonic/reasoning-llama3.2-3b](https://huggingface.co/Isotonic/reasoning-llama3.2-3b) * [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) * [bunnycore/Llama-3.2-3B-Apex](https://huggingface.co/bunnycore/Llama-3.2-3B-Apex) * [TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient](https://huggingface.co/TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient) * [CK0607/llama3.2-3B-CodeP](https://huggingface.co/CK0607/llama3.2-3B-CodeP) * [bunnycore/Llama-3.2-3B-Stock](https://huggingface.co/bunnycore/Llama-3.2-3B-Stock) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - layer_range: [0, 28] model: Hjgugugjhuhjggg/mergekit-ties-qgcitfu parameters: weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Hjgugugjhuhjggg/mergekit-ties-esawwda parameters: weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Hjgugugjhuhjggg/mergekit-ties-dkhnzcn parameters: weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Hjgugugjhuhjggg/mergekit-ties-poovzrh parameters: weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Hjgugugjhuhjggg/mergekit-ties-pghuyfi parameters: weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Hjgugugjhuhjggg/mergekit-ties-kmlzhzo parameters: weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Hjgugugjhuhjggg/mergekit-ties-xflmond parameters: weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Long-Think parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Pure-RP parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Apex parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Mix-Skill parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Booval parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Prodigy parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Sci-Think parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Stock parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: chuanli11/Llama-3.2-3B-Instruct-uncensored parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: ValiantLabs/Llama3.2-3B-Enigma parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: CarrotAI/Llama-3.2-Rabbit-Ko-3B-Instruct parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: AELLM/Llama-3.2-Chibi-3B parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: EmTpro01/llama-3.2-Code-Generator parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: disi-unibo-nlp/llama3.2-3B-SFT-medmcqa-triples-cot parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Atharva26/llama-3.2-3b-mathdaily-chatbot parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Diluksha/Llama_3.2_3B_sql_finetuned_full parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-CodeReactor parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: AcademieDuNumerique/Llama-3.2-3B-SQL-Instruct parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: roger33303/Best_Model-llama3.2-3b-Instruct-Finetune-website-QnA parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: noaebbot/llama3.2-3B-insights parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-TitanFusion-v2 parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-TitanFusion parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: bunnycore/Llama-3.2-3B-Mix parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: ValiantLabs/Llama3.2-3B-ShiningValiant2 parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: BrainWave-ML/llama3.2-3B-codemath-orpo parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: CK0607/llama3.2-3B-CodeP parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: Isotonic/reasoning-llama3.2-3b parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: meta-llama/Llama-3.2-3B-Instruct parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 - layer_range: [0, 28] model: meta-llama/Llama-3.2-3B parameters: weight: 0.5 density: 0.5 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 merge_method: linear base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 parameters: weight: 1 density: 0.9 gamma: 0.01 normalize: true int8_mask: true random_seed: 0 temperature: 0.5 top_p: 0.65 inference: true max_tokens: 999999999 stream: true quantization: - method: int8 value: 100 - method: int4 value: 100 dtype: float16 ```