llava-jp-1.3b-v1.0 / config.json
toshi456's picture
add model weight and config
23cb5d2
raw
history blame
1.2 kB
{
"_name_or_path": "llm-jp/llm-jp-1.3b-v1.0",
"activation_function": "gelu",
"architectures": [
"LlavaGpt2ForCausalLM"
],
"attn_pdrop": 0.1,
"bos_token_id": 7,
"embd_pdrop": 0.1,
"eos_token_id": 7,
"gradient_checkpointing": false,
"image_aspect_ratio": "square",
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"mm_hidden_size": 1024,
"mm_projector_type": "mlp2x_gelu",
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
"model_type": "llava",
"n_ctx": 1024,
"n_embd": 2048,
"n_head": 16,
"n_inner": 8192,
"n_layer": 24,
"n_positions": 2048,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"tokenizer_model_max_length": 1024,
"tokenizer_padding_side": "right",
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 50688
}