Text Generation
Transformers
PyTorch
llava
Inference Endpoints
ChunjiangGe's picture
Upload config.json with huggingface_hub
d218c8c verified
{
"_name_or_path": "ConvLLaVA/ConvLLaVA-pretrain-1024",
"architectures": [
"LlavaLlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"mm_hidden_size": 3072,
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -1,
"mm_vision_tower": "ConvLLaVA/ConvLLaVA-ConvNeXt-1024",
"model_type": "llava",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.33.2",
"tune_entire_model": false,
"tune_mm_mlp_adapter": false,
"tune_vision_tower": true,
"use_cache": false,
"use_mm_proj": true,
"vision_tower_lr": null,
"vocab_size": 32000
}