| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - ibm-granite/granite-8b-code-instruct | |
| - tiiuae/falcon-11B | |
| # merge-LLM-models | |
| merge-LLM-models is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
| * [ibm-granite/granite-8b-code-instruct](https://huggingface.co/ibm-granite/granite-8b-code-instruct) | |
| * [tiiuae/falcon-11B](https://huggingface.co/tiiuae/falcon-11B) | |
| ## 🧩 Configuration | |
| ```yaml{'slices': [{'sources': [{'model': 'ibm-granite/granite-8b-code-instruct', 'layer_range': [0, 12]}, {'model': 'tiiuae/falcon-11B', 'layer_range': [0, 12]}]}], 'merge_method': 'slerp', 'base_model': 'ibm-granite/granite-8b-code-instruct', 'parameters': {'t': [{'filter': 'self_attn', 'value': [0, 0.5, 0.3, 0.7, 1]}, {'filter': 'mlp', 'value': [1, 0.5, 0.7, 0.3, 0]}, {'value': 0.5}]}, 'dtype': 'bfloat16'}``` |