{ "format": "cid-diffusion-base-v1", "base_model": "openbmb/MiniCPM5-2B-Base", "objective": "LLaDA-style masked diffusion", "attention": "bidirectional", "mask_token": "<|cid_mask|>", "mask_token_id": 130560, "sequence_length": 2048, "completed_steps": 5087, "global_batch_size": 96, "tokens_seen": 1000144896, "training_corpus": { "format": "cid-diffusion-stream-v1", "base_model": "openbmb/MiniCPM5-2B-Base", "sequence_length": 2048, "sources": [ { "name": "ultrax-web-en", "repo": "openbmb/UltraX-Preview", "revision": "a88527587389fd4ab352e9ad1273f4c0a234d8df", "pattern": "data/UltraX-Ultra-FineWeb/*.parquet", "column": "cleaned_content", "weight": 0.7 }, { "name": "ultrafineweb-zh", "repo": "openbmb/Ultra-FineWeb", "revision": "02c85641e3d19a854be2e09139c25adaa9518063", "pattern": "data/ultrafineweb_zh/*.parquet", "column": "content", "weight": 0.15 }, { "name": "ultradata-code", "repo": "openbmb/UltraData-Code", "revision": "85182d829f2ce7ea07cca72ebfc509deea1d9f5f", "pattern": "data/UltraData-Code-L2/*/*.parquet", "column": "content", "weight": 0.1 }, { "name": "ultradata-math", "repo": "openbmb/UltraData-Math", "revision": "fe10db8efd35597fd7fcff8ff576b5ec4ea5ff87", "pattern": "data/UltraData-Math-L2-preview/*.parquet", "column": "content", "weight": 0.05 } ] }, "mask_ratio_range": [ 0.001, 1.0 ], "hf_loader": "CIDDiffusionForMaskedLM", "hf_auto_model": "AutoModelForCausalLM", "requires_trust_remote_code": true }