| { |
| "ada_dlm_loss_ratio": null, |
| "ada_perm_ratio_global": null, |
| "ada_perm_ratio_per_block": null, |
| "adaptive_mask_rate": false, |
| "ar_loss_weight": 1.0, |
| "architectures": [ |
| "MinistralDiffEncoderModel" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_implementation": "sdpa", |
| "auto_map": { |
| "AutoConfig": "configuration_ministral_dlm.MinistralDLMConfig", |
| "AutoModel": "modeling_ministral_dlm.MinistralDiffEncoderModel" |
| }, |
| "block_size": 32, |
| "bos_token_id": 1, |
| "diff_loss_weight": 1, |
| "dlm_arch": "encoder", |
| "dlm_loss_weight": null, |
| "dlm_paradigm": "bidirectional", |
| "dlm_type": "llada", |
| "dp_varying_mask_ratio": false, |
| "enable_self_spec": false, |
| "enforce_mask": false, |
| "eos_token_id": 11, |
| "global_loss_avg": false, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 3072, |
| "initializer_range": 0.02, |
| "intermediate_size": 9216, |
| "mask_token_id": 100, |
| "max_position_embeddings": 262144, |
| "mlp_bias": false, |
| "model_type": "ministral_dlm", |
| "multi_sampling": null, |
| "num_ar_layers": 0, |
| "num_attention_heads": 32, |
| "num_diffusion_layers": 0, |
| "num_hidden_layers": 26, |
| "num_key_value_heads": 8, |
| "num_skip_loss_tokens": 0, |
| "prefix_ratio": 0.8, |
| "random_length_prob": 0, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 16.0, |
| "llama_4_scaling_beta": 0.1, |
| "mscale": 1.0, |
| "mscale_all_dim": 1.0, |
| "original_max_position_embeddings": 16384, |
| "rope_theta": 1000000.0, |
| "rope_type": "yarn", |
| "type": "yarn" |
| }, |
| "rope_scaling": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 16.0, |
| "llama_4_scaling_beta": 0.1, |
| "mscale": 1.0, |
| "mscale_all_dim": 1.0, |
| "original_max_position_embeddings": 16384, |
| "rope_theta": 1000000.0, |
| "rope_type": "yarn", |
| "type": "yarn" |
| }, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "tok_mask_half_life_ratio": null, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.55.4", |
| "use_cache": false, |
| "vocab_size": 131072 |
| } |
|
|
