Jofthomas's picture
Final improvements (#3)
bf37fea verified
{
"architectures": [
"Mistral3ForConditionalGeneration"
],
"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": 3072,
"initializer_range": 0.02,
"intermediate_size": 9216,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 262144,
"model_type": "ministral",
"num_attention_heads": 32,
"num_hidden_layers": 26,
"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,
"tie_word_embeddings": true,
"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,
"transformers.js_config": {
"dtype": {
"decoder_model_merged": "q4f16",
"vision_encoder": "fp16",
"embed_tokens": "fp16"
},
"use_external_data_format": {
"embed_tokens.onnx": 1,
"embed_tokens_fp16.onnx": 1,
"embed_tokens_quantized.onnx": 1,
"embed_tokens_q4.onnx": 1,
"embed_tokens_q4f16.onnx": 1,
"vision_encoder.onnx": 1,
"vision_encoder_fp16.onnx": 1,
"vision_encoder_quantized.onnx": 1,
"vision_encoder_q4.onnx": 1,
"vision_encoder_q4f16.onnx": 1,
"decoder_model_merged.onnx": 7,
"decoder_model_merged_fp16.onnx": 4,
"decoder_model_merged_quantized.onnx": 2,
"decoder_model_merged_q4.onnx": 2,
"decoder_model_merged_q4f16.onnx": 1
},
"kv_cache_dtype": {
"q4f16": "float16",
"fp16": "float16"
}
}
}