majentik's picture
Add MLX quantized model weights
b85864d verified
{
"eos_token_id": 2,
"image_token_index": 10,
"model_type": "mistral3",
"multimodal_projector_bias": false,
"projector_hidden_act": "gelu",
"quantization": {
"group_size": 64,
"bits": 8,
"mode": "affine",
"language_model.model.layers.0.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.1.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.2.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.3.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.4.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.5.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.6.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.7.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.8.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.9.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.10.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.11.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.12.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.13.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.14.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.15.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.16.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.17.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.18.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.19.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.20.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.21.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.22.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.23.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.24.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.25.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.26.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.27.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.28.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.29.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.30.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.31.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.32.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.33.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.34.mlp.gate": {
"group_size": 64,
"bits": 8
},
"language_model.model.layers.35.mlp.gate": {
"group_size": 64,
"bits": 8
}
},
"quantization_config": {
"group_size": 64,
"bits": 2,
"mode": "affine",
"language_model.model.layers.0.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.1.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.2.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.3.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.4.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.5.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.6.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.7.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.8.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.9.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.10.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.11.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.12.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.13.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.14.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.15.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.16.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.17.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.18.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.19.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.20.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.21.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.22.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.23.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.24.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.25.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.26.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.27.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.28.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.29.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.30.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.31.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.32.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.33.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.34.mlp.gate": {
"group_size": 64,
"bits": 2
},
"language_model.model.layers.35.mlp.gate": {
"group_size": 64,
"bits": 2
}
},
"spatial_merge_size": 2,
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"first_k_dense_replace": 0,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"kv_lora_rank": 256,
"max_position_embeddings": 1048576,
"model_type": "mistral4",
"moe_intermediate_size": 2048,
"n_group": 1,
"n_routed_experts": 128,
"n_shared_experts": 1,
"norm_topk_prob": true,
"num_attention_heads": 32,
"num_experts_per_tok": 4,
"num_hidden_layers": 36,
"num_key_value_heads": 32,
"pad_token_id": 11,
"pretraining_tp": 1,
"q_lora_rank": 1024,
"qk_head_dim": 128,
"qk_nope_head_dim": 64,
"qk_rope_head_dim": 64,
"rms_norm_eps": 1e-06,
"rope_interleave": true,
"rope_parameters": {
"beta_fast": 32.0,
"beta_slow": 1.0,
"factor": 128.0,
"llama_4_scaling_beta": 0.1,
"mscale": 1.0,
"mscale_all_dim": 1.0,
"original_max_position_embeddings": 8192,
"partial_rotary_factor": 0.5,
"rope_theta": 10000.0,
"rope_type": "yarn",
"type": "yarn"
},
"routed_scaling_factor": 1.0,
"sliding_window": null,
"tie_word_embeddings": false,
"topk_group": 1,
"use_cache": true,
"v_head_dim": 128,
"vocab_size": 131072
},
"tie_word_embeddings": false,
"transformers_version": "5.3.0.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"
}
},
"vision_feature_layer": -1
}