| { | |
| "experts": [ | |
| "mistralai/Mistral-7B-Instruct-v0.2", | |
| "Qwen/Qwen2.5-7B-Instruct" | |
| ], | |
| "top_k": 1, | |
| "router_encoder": "distilbert-base-uncased", | |
| "max_new_tokens": 256, | |
| "description": "Claude-style MoE with lazy-loaded 4-bit experts" | |
| } |
| { | |
| "experts": [ | |
| "mistralai/Mistral-7B-Instruct-v0.2", | |
| "Qwen/Qwen2.5-7B-Instruct" | |
| ], | |
| "top_k": 1, | |
| "router_encoder": "distilbert-base-uncased", | |
| "max_new_tokens": 256, | |
| "description": "Claude-style MoE with lazy-loaded 4-bit experts" | |
| } |