| { | |
| "_name_or_path": "/home/aiops/yangph/checkpoints/glide/checkpoint/experiments/qwq32b-slim6b.glide.A100.tp1dp1.zero1.v1.0.sinkpi-slicing.longv2-32k-5e-6.lig-ce.no-mask.longcot-5e-6.s42/checkpoint-last", | |
| "architectures": [ | |
| "Qwen2GlideDecoderLayer" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27648, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 64, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 151643, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |