llava-1.6-sft / config.json
VPeterV
upload model
d11f548
{
"_name_or_path": "SurfaceData/llava-v1.6-mistral-7b-sglang",
"architectures": [
"LlavaLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"freeze_mm_vision_resampler": false,
"hidden_act": "silu",
"hidden_size": 4096,
"ignore_index": -100,
"image_aspect_ratio": "pad",
"image_crop_resolution": 224,
"image_grid_pinpoints": [
[
336,
672
],
[
672,
336
],
[
672,
672
],
[
1008,
336
],
[
336,
1008
]
],
"image_split_resolution": 224,
"image_token_index": 32000,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"mm_hidden_size": 1024,
"mm_patch_merge_type": "flat",
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_resampler_type": null,
"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": "openai/clip-vit-large-patch14-336",
"mm_vision_tower_lr": 2e-06,
"model_type": "llava",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"projector_hidden_act": "gelu",
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"text_config": {
"model_type": "llama"
},
"tie_word_embeddings": false,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.38.0",
"tune_entire_model": false,
"tune_mm_mlp_adapter": false,
"tune_mm_vision_resampler": false,
"tune_vision_tower": false,
"unfreeze_mm_vision_tower": true,
"use_cache": true,
"use_mm_proj": true,
"vision_config": {
"hidden_size": 1024,
"image_size": 336,
"intermediate_size": 4096,
"model_type": "clip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"patch_size": 14,
"projection_dim": 768,
"vocab_size": 32000
},
"vision_feature_layer": -2,
"vision_feature_select_strategy": "default",
"vocab_size": 32000,
"white_bg": true
}