Init

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f8e560a0796027f99bc77987bdca34a1331cc62e8828aa759889c2d05e442a
+size 639692768

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": [
+    1280,
+    1280,
+    640,
+    320,
+    1024
+  ],
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "SDCLIPBlock",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_resolution": 384,
+  "mm_vision_sd_clip": "openai/clip-vit-large-patch14-336",
+  "mm_vision_sd_clip_proj_in": 1024,
+  "mm_vision_sd_clip_proj_out": 768,
+  "mm_vision_sd_concat_clip": true,
+  "mm_vision_sd_ensemble_size": 1,
+  "mm_vision_sd_implicit_caption": true,
+  "mm_vision_sd_pe": 576,
+  "mm_vision_sd_timestep": 100,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": 1,
+  "mm_vision_tower": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "model_type": "llava_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": "float16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48de13cc0960110c68da3da7233c6dd9effa420844bce07e8d55c9eeab01b973
+size 61340996