| { | |
| "_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_7B_ext_u48_part1-2_lr1e4_wsd_bs128_peft_32_32_lm_head_1e4_v7_1m_v7/kto2", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "dual_chunk_attention_config": { | |
| "chunk_size": 262144, | |
| "local_size": 8192, | |
| "original_max_position_embeddings": 262144 | |
| }, | |
| "eos_token_id": 145111, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 1010000, | |
| "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-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.45.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 145152 | |
| } | |