| { | |
| "_model_name_or_path": "sakura-13b-ft_0514_1epoch_qwen2beta_32b_base_full_r128_v1", | |
| "_name_or_path": "SakuraLLM/Sakura-32B-Qwen2beta-v0.9-GGUF", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27392, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 151643, | |
| "rms_norm_eps": 9.999999974752427e-07, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.45.0.dev0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |