Ba2han's picture
Upload Mistral3ForConditionalGeneration
b7b2715 verified
{
"architectures": [
"Mistral3ForConditionalGeneration"
],
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"image_token_index": 10,
"model_type": "mistral3",
"multimodal_projector_bias": false,
"pad_token_id": 11,
"projector_hidden_act": "gelu",
"quantization_config": {
"config_groups": {
"MXFP4": {
"format": "mxfp4-pack-quantized",
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": 32,
"num_bits": 4,
"observer": null,
"observer_kwargs": {},
"scale_dtype": "torch.uint8",
"strategy": "group",
"symmetric": true,
"type": "float",
"zp_dtype": null
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": 32,
"num_bits": 4,
"observer": "static_minmax",
"observer_kwargs": {},
"scale_dtype": "torch.uint8",
"strategy": "group",
"symmetric": true,
"type": "float",
"zp_dtype": null
}
}
},
"format": "mxfp4-pack-quantized",
"global_compression_ratio": null,
"ignore": [
"re:.*gate$",
"lm_head",
"re:.*kv_a_proj_with_mqa$",
"re:.*q_a_proj$",
"model.embed_tokens",
"re:.*vision_tower.*",
"re:.*multi_modal_projector.*",
"re:.*merger.*",
"re:.*embed_tokens.*"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {}
},
"spatial_merge_size": 2,
"text_config": {
"attention_dropout": 0.0,
"dtype": "bfloat16",
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 262144,
"model_type": "ministral3",
"num_attention_heads": 32,
"num_hidden_layers": 34,
"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": 1000000.0,
"rope_type": "yarn",
"type": "yarn"
},
"sliding_window": null,
"use_cache": true,
"vocab_size": 131072
},
"tie_word_embeddings": false,
"transformers_version": "5.0.0.dev0",
"unsloth_fixed": true,
"unsloth_version": "2025.12.9",
"use_cache": false,
"vision_config": {
"attention_dropout": 0.0,
"dtype": "bfloat16",
"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
}