| { | |
| "architectures": [ | |
| "SDLMQwen2ForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_sdlm.SDLMQwen2Config", | |
| "AutoModelForCausalLM": "modeling_sdlm.SDLMQwen2ForCausalLM" | |
| }, | |
| "attention_dropout": 0.0, | |
| "attn_implementation": "eager", | |
| "block_size": 4, | |
| "bos_token_id": 151643, | |
| "casual_attn": false, | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27648, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 64, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 131072, | |
| "text_mask_token": "<text_mask>", | |
| "text_mask_token_id": 151665, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151666 | |
| } | |