{ "architectures": [ "KsByteForCausalLM" ], "auto_map": { "AutoConfig": "configuration_ksbyte.KsByteConfig", "AutoModelForCausalLM": "modeling_ksbyte.KsByteForCausalLM", "AutoTokenizer": [ "tokenization_ksbyte.KsByteTokenizer", null ] }, "batch_size": 16, "best_val_bpb": 0.9592911933406559, "beta1": 0.9, "beta2": 0.95, "bf16": true, "bos_token_id": 256, "byte_vocab": 256, "ctx_len": 2048, "d_model": 384, "data_dir": "/cache/data", "data_meta": { "bos_id": 256, "bytes_per_word": 9.865595756933395, "counts": { "test": 3074698, "train": 45362173, "val": 1622371 }, "dtype": "uint16", "eos_id": 257, "normalization": { "digit_policy": "keep_native", "remove_diacritics": false, "zwnj_policy": "keep" }, "source": "Omarrran/KS-PRET-5M_5_million_kashmiri_Pretrainning_LLM_dataset_12M_tokens_2026", "stats": { "content_bytes": 50058684, "dropped_dup": 0, "dropped_ksr": 0, "dropped_short": 0, "kept": 279, "raw": 279, "words": 5074066 }, "vocab_size": 259 }, "dedup": true, "device": "auto", "digit_policy": "keep_native", "doc_attention_mask": true, "dropout": 0.1, "dtype": "float32", "early_stop_patience": 6, "eos_token_id": 257, "epochs": 4.0, "eval_interval": 250, "eval_iters": 100, "generate_every": 1000, "generate_tokens": 160, "grad_accum": 4, "grad_clip": 1.0, "hf_dataset": "Omarrran/KS-PRET-5M_5_million_kashmiri_Pretrainning_LLM_dataset_12M_tokens_2026", "hf_revision": null, "keep_mixed_script": true, "label_smoothing": 0.0, "local_text_file": null, "log_interval": 20, "lr": 0.0004, "max_chars": 100000, "max_patches": 320, "max_steps": 5000, "min_chars": 2, "min_ks_ratio": 0.9, "min_lr_ratio": 0.1, "mlp_ratio": 2.6667, "model_type": "ksbyte", "n_global": 6, "n_heads": 6, "n_kv_heads": 2, "n_layers": 6, "n_local_in": 2, "n_local_out": 2, "num_workers": 4, "output_dir": "/outputs", "pad_token_id": 258, "qk_norm": true, "rebuild_data": false, "remove_diacritics": false, "resume": "auto", "rope_theta": 10000.0, "run_name": "ksbyte-spacebyte-full", "save_interval": 100, "save_total_limit": 3, "seed": 42, "source_checkpoint": "best.pt", "split_seed": 13, "test_frac": 0.05, "text_col": "auto", "tf32": true, "tie_embeddings": true, "torch_compile": false, "training_step": 3250, "transformers_compatible_revision": "v1", "transformers_version": "4.57.6", "use_cache": false, "use_wandb": false, "val_frac": 0.05, "variant": "spacebyte", "vocab_size": 259, "wandb_project": "ks-byte-lm", "warmup_ratio": 0.03, "weight_decay": 0.1, "z_loss_weight": 0.0001, "zwnj_policy": "keep", "library_name": "transformers" }