jina-clip-v2 / config.json
gmastrapas's picture
fix: enable flash-attn and xformers by default
ced12ef
{
"add_projections": false,
"architectures": [
"JinaCLIPModel"
],
"auto_map": {
"AutoConfig": "jinaai/jina-clip-implementation--configuration_clip.JinaCLIPConfig",
"AutoModel": "jinaai/jina-clip-implementation--modeling_clip.JinaCLIPModel"
},
"initializer_factor": 1.0,
"logit_scale_init_value": 2.6592,
"matryoshka_dimensions": [32, 64, 128, 256, 512, 768, 1024],
"model_type": "jina_clip",
"projection_dim": 1024,
"text_config": {
"default_instruction_task": null,
"default_lora_task": "retrieval.query",
"embed_dim": 1024,
"hf_model_config_kwargs": {
"load_trained_adapters": false,
"lora_adaptations": [
"retrieval.query"
],
"lora_alpha": 4,
"lora_dropout_p": 0.0,
"lora_main_params_trainable": false,
"lora_rank": 4,
"task_instructions": {
"retrieval.query": "Represent the query for retrieving evidence documents: "
},
"use_flash_attn": true
},
"hf_model_name_or_path": "jinaai/jina-embeddings-v3",
"model_type": "jina_clip_text",
"pooler_type": "mean_pooler",
"proj_bias": false,
"proj_type": null
},
"torch_dtype": "bfloat16",
"truncate_dim": null,
"use_text_flash_attn": null,
"use_vision_xformers": null,
"vision_config": {
"embed_dim": 1024,
"fused_layer_norm": false,
"head_width": 64,
"image_size": 512,
"intp_freq": true,
"layers": 24,
"ls_init_value": null,
"mlp_ratio": 2.6667,
"model_type": "jina_clip_vision",
"naive_swiglu": true,
"patch_dropout": 0.1,
"patch_size": 14,
"post_norm": false,
"proj_type": null,
"pt_hw_seq_len": 16,
"qkv_bias": true,
"rope_embeddings": true,
"subln": true,
"width": 1024,
"x_attention": true
}
}