| { | |
| "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 | |
| }, | |
| "model_type": "kraken", | |
| "models": { | |
| "expert1": "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct", | |
| "expert2": "mii-community/zefiro-7b-dpo-ITA", | |
| "expert3": "paulml/Hermes-2-Pro-French", | |
| "expert4": "norallm/normistral-7b-warm-instruct" | |
| }, | |
| "quantization": { | |
| "expert1": null, | |
| "expert2": null, | |
| "expert3": null, | |
| "expert4": null | |
| }, | |
| "router": "kraken_router", | |
| "tokenizers": { | |
| "expert1": "VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct", | |
| "expert2": "mii-community/zefiro-7b-dpo-ITA", | |
| "expert3": "paulml/Hermes-2-Pro-French", | |
| "expert4": "norallm/normistral-7b-warm-instruct" | |
| } | |
| }, | |
| "model_type": "kraken", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.0" | |
| } | |