LongLLaVA-53B-A13B / config.json
Xidong's picture
Upload config.json with huggingface_hub
10f8024 verified
raw
history blame
1.97 kB
{
"_name_or_path": "/wangbenyou/xidong/VisionJamba/ckpts/visionjambaSFT40PoolConcat2D",
"architectures": [
"LlavaJambaForCausalLM"
],
"attention_dropout": 0.0,
"attn_layer_offset": 4,
"attn_layer_period": 8,
"auto_map": {
"AutoConfig": "configuration_jamba.JambaConfig",
"AutoModel": "modeling_jamba.JambaModel",
"AutoModelForCausalLM": "modeling_jamba.JambaForCausalLM",
"AutoModelForSequenceClassification": "model.JambaForSequenceClassification"
},
"bos_token_id": 1,
"calc_logits_for_entire_prompt": false,
"eos_token_id": 2,
"expert_layer_offset": 1,
"expert_layer_period": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 14336,
"mamba_conv_bias": true,
"mamba_d_conv": 4,
"mamba_d_state": 16,
"mamba_dt_rank": 256,
"mamba_expand": 2,
"mamba_inner_layernorms": true,
"mamba_proj_bias": false,
"mm_hidden_size": 1024,
"mm_patch_merge_type": "flat",
"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": -2,
"mm_vision_tower": "/wangbenyou/guimingchen/models/clip_vit_large_patch14_336",
"model_type": "llava_jamba",
"n_ctx": 262144,
"num_attention_heads": 32,
"num_experts": 16,
"num_experts_per_tok": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"output_router_logits": false,
"pad_token_id": 0,
"resamplePooling": "2d",
"rms_norm_eps": 1e-06,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 40960,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.42.3",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mamba_kernels": true,
"use_mm_proj": true,
"vocab_size": 65536
}