| { | |
| "architectures": [ | |
| "KrakenForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_kraken.KrakenConfig", | |
| "AutoModel": "modeling_kraken.KrakenForCausalLM", | |
| "AutoModelForCausalLM": "modeling_kraken.KrakenForCausalLM" | |
| }, | |
| "config_dict": { | |
| "class_indices": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2, | |
| "LABEL_3": 3, | |
| "LABEL_4": 4 | |
| }, | |
| "model_type": "kraken", | |
| "models": { | |
| "expert1": "microsoft/Phi-3-medium-128k-instruct", | |
| "expert2": "gorilla-llm/gorilla-openfunctions-v2", | |
| "expert3": "ise-uiuc/Magicoder-S-DS-6.7B", | |
| "expert4": "defog/llama-3-sqlcoder-8b", | |
| "expert5": "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct" | |
| }, | |
| "quantization": { | |
| "expert1": null, | |
| "expert2": null, | |
| "expert3": null, | |
| "expert4": null, | |
| "expert5": null | |
| }, | |
| "router": "./kraken_router", | |
| "tokenizers": { | |
| "expert1": "microsoft/Phi-3-medium-128k-instruct", | |
| "expert2": "gorilla-llm/gorilla-openfunctions-v2", | |
| "expert3": "ise-uiuc/Magicoder-S-DS-6.7B", | |
| "expert4": "defog/llama-3-sqlcoder-8b", | |
| "expert5": "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct" | |
| } | |
| }, | |
| "model_type": "kraken", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.0" | |
| } | |