File size: 1,365 Bytes
a424b3c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
{
"_name_or_path": "42dot/42dot_LLM-SFT-1.3B",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50257,
"eos_token_id": 50256,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 2048,
"image_aspect_ratio": "square",
"image_projector_type": "mlp2x_gelu",
"initializer_range": 0.01,
"intermediate_size": 5632,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"mm_image_tower": "openai/clip-vit-large-patch14-336",
"mm_projector_lr": null,
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_video_tower": null,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"model_type": "llava_llama",
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 32,
"pad_token_id": 50259,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"tokenizer_class": "GPT2TokenizerFast",
"tokenizer_padding_side": "right",
"torch_dtype": "float32",
"transformers_version": "4.37.0",
"tune_mm_mlp_adapter": true,
"use_cache": true,
"use_mm_proj": true,
"video_global_proj": false,
"video_projector_type": "linear",
"video_spatial_proj": false,
"video_temproal_proj": false,
"vocab_size": 50304
}
|