| { | |
| "_name_or_path": "/mnt/bn/mllmhl/sft_checkpoints/qwen2.5-14b-ts-explaints-1124-stage1-sp/checkpoint-400", | |
| "architectures": [ | |
| "Qwen2TSForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_qwen2.Qwen2TSConfig", | |
| "AutoModel": "modeling_qwen2.Qwen2TSForCausalLM", | |
| "AutoModelForCausalLM": "modeling_qwen2.Qwen2TSForCausalLM" | |
| }, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "ignore_index": -100, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 70, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 151643, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.46.2", | |
| "ts": { | |
| "hidden_size": 5120, | |
| "num_features": 2, | |
| "num_layers": 5, | |
| "patch_size": 16 | |
| }, | |
| "ts_token_end_index": 151665, | |
| "ts_token_start_index": 151666, | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |