Delete captioner

captioner/adapter_config.json

@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "llava-v1.5-13b",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "lora_alpha": 256,
-  "lora_dropout": 0.05,
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 128,
-  "revision": null,
-  "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "q_proj",
-    "v_proj",
-    "o_proj",
-    "k_proj",
-    "down_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}

captioner/adapter_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a75d4904466df96ba770230d096e0e976e3c0cd67b62c93e383cac35def1dbad
-size 2002974413

captioner/config.json

@@ -1,45 +0,0 @@
-{
-  "_name_or_path": "captioner",
-  "architectures": [
-    "LlavaLlamaForCausalLM"
-  ],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "freeze_mm_mlp_adapter": false,
-  "freeze_mm_vision_resampler": false,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "image_aspect_ratio": "pad",
-  "initializer_range": 0.02,
-  "intermediate_size": 13824,
-  "max_length": 4096,
-  "max_position_embeddings": 4096,
-  "mm_hidden_size": 1024,
-  "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": "/mnt/workspace/workgroup/temporary/zhantao/BACON/ckpt/clip-vit-large-patch14-336",
-  "model_type": "llava_llama",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 40,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 4096,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
-  "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
-}

captioner/non_lora_trainables.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de935c4cc6ef5ed1f0a883fd80874aac46e17d5bcc4f28f68de5cc2f30717898
-size 62936807