| base_model: | |
| - KissanAI/llama3-8b-dhenu-0.1-sft-16bit | |
| - unsloth/llama-3-8b-Instruct | |
| - Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1 | |
| library_name: transformers | |
| tags: | |
| - mergekit | |
| - merge | |
| # llama3-Fasal-Mitra | |
| 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 [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [unsloth/llama-3-8b-Instruct](https://huggingface.co/unsloth/llama-3-8b-Instruct) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [KissanAI/llama3-8b-dhenu-0.1-sft-16bit](https://huggingface.co/KissanAI/llama3-8b-dhenu-0.1-sft-16bit) | |
| * [Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1](https://huggingface.co/Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| models: | |
| - model: unsloth/llama-3-8b-Instruct | |
| parameters: | |
| weight: 0.20 | |
| - model: Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1 | |
| parameters: | |
| weight: 0.40 | |
| - model: KissanAI/llama3-8b-dhenu-0.1-sft-16bit | |
| parameters: | |
| weight: 0.40 | |
| base_model: unsloth/llama-3-8b-Instruct | |
| merge_method: task_arithmetic | |
| dtype: bfloat16 | |
| ``` | |