| { |
| "_name_or_path": "/hkfs/work/workspace/scratch/lmu_chd4938-MINED_26/null_space_sample_specific_know/lora_null_sample_ckpt/llava_rank128_MathVision_MathVista_MINI_pre_128", |
| "architectures": [ |
| "CovSVDLlavaLlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_oursvd_llama.CovSVDLlamaConfig", |
| "AutoModelForCausalLM": "modeling_oursvd_llama.CovSVDLlamaForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "freeze_mm_mlp_adapter": false, |
| "freeze_mm_vision_resampler": false, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "image_aspect_ratio": "pad", |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "lora_r": 128, |
| "max_length": 4096, |
| "max_position_embeddings": 4096, |
| "mlp_bias": false, |
| "mm_hidden_size": 1024, |
| "mm_patch_merge_type": "flat", |
| "mm_projector_lr": 2e-05, |
| "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": "/hkfs/work/workspace/scratch/lmu_chd4938-MINED_26/MINED_26/data_ckpt/vlm_ckpt/clip-vit-large-patch14-336", |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "tokenizer_model_max_length": 2048, |
| "tokenizer_padding_side": "right", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.37.2", |
| "truncation_ranks": null, |
| "tune_mm_mlp_adapter": false, |
| "tune_mm_vision_resampler": false, |
| "unfreeze_mm_vision_tower": false, |
| "use_cache": true, |
| "use_mm_proj": true, |
| "vocab_size": 32000 |
| } |
|
|
