| { |
| "architectures": [ |
| "MinivoxtralForConditionalGeneration" |
| ], |
| "dtype": "bfloat16", |
| "image_token_index": 10, |
| "model_type": "mistral3", |
| "multimodal_projector_bias": false, |
| "projector_hidden_act": "gelu", |
| "spatial_merge_size": 2, |
| "text_config": { |
| "attention_dropout": 0.0, |
| "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, |
| "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, |
| "use_cache": true, |
| "vocab_size": 131072 |
| }, |
| "transformers_version": "5.0.0.dev0", |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "image_size": 1540, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "model_type": "pixtral", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 24, |
| "patch_size": 14, |
| "rope_parameters": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| }, |
| "rope_theta": 10000.0 |
| }, |
| "vision_feature_layer": -1, |
| "audio_config": { |
| "activation_dropout": 0.0, |
| "activation_function": "gelu", |
| "attention_dropout": 0.0, |
| "dropout": 0.0, |
| "head_dim": 64, |
| "hidden_size": 1280, |
| "initializer_range": 0.02, |
| "intermediate_size": 5120, |
| "layerdrop": 0.0, |
| "max_source_positions": 1500, |
| "model_type": "voxtral_encoder", |
| "num_attention_heads": 20, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 20, |
| "num_mel_bins": 128, |
| "sampling_rate": 16000, |
| "hop_length": 160, |
| "window_size": 400, |
| "downsample_factor": 4, |
| "scale_embedding": false, |
| "vocab_size": 51866 |
| }, |
| "audio_token_id": 24, |
| "audio_downsample_factor": 4, |
| "audio_projector_hidden_act": "gelu", |
| "audio_multimodal_projector_bias": false, |
| "quantization_config": { |
| "bits": 4, |
| "checkpoint_format": "gptq", |
| "desc_act": false, |
| "format": "gptq", |
| "group_size": 64, |
| "lm_head": false, |
| "meta": { |
| "act_group_aware": true, |
| "damp_auto_increment": 0.01, |
| "damp_percent": 0.05, |
| "gptaq": false, |
| "gptaq_alpha": 0.25, |
| "mse": 0.0, |
| "quantizer": [ |
| "gptqmodel:5.6.12" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel" |
| }, |
| "pack_dtype": "int32", |
| "pack_impl": "cpu", |
| "quant_method": "gptq", |
| "sym": true |
| } |
| } |
