{ "_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_t-lite-base-v1_ext_u48_part1-2_lr1e4_wsd_bs128_peft_32_32_qvkogud_lh_1e4_v7_v7/kto2", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "eos_token_id": 145111, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "pad_token_id": 145109, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "use_cache": false, "use_sliding_window": false, "vocab_size": 145152 }