liuhaotian's picture
Update config.json
e3b2e6f
raw
history blame
1.5 kB
{
"_name_or_path": "llava-mpt-7b-pretrain_blip_558k_new_template_1e-instruct_conv_reason_nooverlap_80k-1epoch",
"architectures": [
"LlavaMPTForCausalLM"
],
"attn_config": {
"alibi": true,
"alibi_bias_max": 8,
"attn_impl": "torch",
"attn_pdrop": 0,
"attn_type": "multihead_attention",
"attn_uses_sequence_id": false,
"clip_qkv": null,
"prefix_lm": false,
"qk_ln": false,
"softmax_scale": null
},
"d_model": 4096,
"emb_pdrop": 0,
"embedding_fraction": 1.0,
"expansion_ratio": 4,
"freeze_mm_mlp_adapter": false,
"init_config": {
"emb_init_std": null,
"emb_init_uniform_lim": null,
"fan_mode": "fan_in",
"init_div_is_residual": true,
"init_gain": 0,
"init_nonlinearity": "relu",
"init_std": 0.02,
"name": "kaiming_normal_",
"verbose": 0
},
"init_device": "cpu",
"learned_pos_emb": true,
"logit_scale": null,
"max_seq_len": 2048,
"mm_hidden_size": 1024,
"mm_use_im_start_end": true,
"mm_vision_select_layer": -2,
"mm_vision_tower": "openai/clip-vit-large-patch14",
"model_type": "llava_mpt",
"n_heads": 32,
"n_layers": 32,
"no_bias": true,
"norm_type": "low_precision_layernorm",
"resid_pdrop": 0,
"sep_image_conv_front": false,
"tokenizer_name": "sam-mosaic/gpt-neox-20b-chatml",
"torch_dtype": "float16",
"transformers_version": "4.28.0.dev0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"verbose": 0,
"vocab_size": 50282
}