{"status":"ok","model":{"name":"Intern-Decision-4B","source":"internlm/Intern-Decision-4B","revision":"0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd","checkpoint":"/hf/hub/models--internlm--Intern-Decision-4B/snapshots/0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd","inference_py_sha256":"c904e2c67ca0775621a22375ee373d2ba30b52117cda870c6c9ef74143b29863","temperature":1.99241824,"dtype":"bfloat16","attn_implementation":"sdpa","device":"cuda","max_length":8192,"torch_version":"2.10.0+cu128","transformers_version":"5.17.0","vision_tower":"removed","device_name":"NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition","allocated_gib":7.937,"reserved_gib":8.082,"max_reserved_gib":8.861},"vram_cap_gib":9.25,"max_tokens":8192,"max_decisions":64,"max_questions_per_call":16,"chunking":"/decide/shared questions are packed greedily, in request order, into calls of at most 16 (1-16, 17-32, ...); each call is one prompt, so the questions in a call are asked together. With orderings, ordering k of every decision forms wave k, packed the same way.","workloads":[]}