| { | |
| "architectures": [ | |
| "Ministral3ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 16384, | |
| "max_position_embeddings": 262144, | |
| "model_type": "ministral3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 11, | |
| "quantization_config": { | |
| "activation_scheme": "static", | |
| "dequantize": false, | |
| "modules_to_not_convert": [ | |
| "model.vision_tower", | |
| "model.multi_modal_projector", | |
| "lm_head", | |
| "model.vision_tower", | |
| "model.multi_modal_projector", | |
| "lm_head" | |
| ], | |
| "quant_method": "fp8", | |
| "weight_block_size": null | |
| }, | |
| "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": 1000000000.0, | |
| "rope_type": "yarn", | |
| "type": "yarn" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.0.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| } | |