| { | |
| "architectures": [ | |
| "DharaForMaskedDiffusion" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "modeling_dhara.DharaConfig", | |
| "AutoModel": "modeling_dhara.DharaForMaskedDiffusion", | |
| "AutoModelForCausalLM": "modeling_dhara.DharaForMaskedDiffusion" | |
| }, | |
| "bos_token_id": 1, | |
| "canon_activation": false, | |
| "canon_bias": false, | |
| "canon_kernel": 4, | |
| "canon_residual": true, | |
| "canon_set": "AC", | |
| "eos_token_id": 2, | |
| "head_dim": 48, | |
| "hidden_act": "silu", | |
| "hidden_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "mask_epsilon": 0.001, | |
| "mask_token_id": 50256, | |
| "max_position_embeddings": 1024, | |
| "model_type": "dhara", | |
| "num_attention_heads": 8, | |
| "num_diffusion_steps": 1000, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.2", | |
| "use_cache": false, | |
| "use_flash_attention": false, | |
| "use_xformers": false, | |
| "vocab_size": 50304 | |
| } | |