Upload B2 DPO PPO linear model soup adapter

README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+tags:
+- peft
+- lora
+- visual-question-answering
+base_model: chaoyinshe/llava-med-v1.5-mistral-7b-hf
+---
+
+# Medical VQA Merged Adapter
+
+Merge method: `linear`
+
+| Adapter | Weight |
+|---|---:|
+| `/Users/springwang/Library/Mobile Documents/com~apple~CloudDocs/juniorYear/DeepLearning/Final_523H0173_523H0178/DL_MedicalVQA_Project/checkpoints/B2/checkpoint-3355` | 0.4000 |
+| `/Users/springwang/Library/Mobile Documents/com~apple~CloudDocs/juniorYear/DeepLearning/Final_523H0173_523H0178/DL_MedicalVQA_Project/checkpoints/DPO/final_adapter` | 0.3000 |
+| `/Users/springwang/Library/Mobile Documents/com~apple~CloudDocs/juniorYear/DeepLearning/Final_523H0173_523H0178/DL_MedicalVQA_Project/checkpoints/PPO/final_adapter` | 0.3000 |
+
+This adapter was created by merging fine-tuned LoRA adapters without additional training.

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "chaoyinshe/llava-med-v1.5-mistral-7b-hf",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10bc5a80ba0db34d3aaa46a8ff2e59799283a922f8766a214471e11c7ab0f564
+size 177298808

merge_config.json

@@ -0,0 +1,14 @@
+{
+  "method": "linear",
+  "base_model": "chaoyinshe/llava-med-v1.5-mistral-7b-hf",
+  "adapters": [
+    "/Users/springwang/Library/Mobile Documents/com~apple~CloudDocs/juniorYear/DeepLearning/Final_523H0173_523H0178/DL_MedicalVQA_Project/checkpoints/B2/checkpoint-3355",
+    "/Users/springwang/Library/Mobile Documents/com~apple~CloudDocs/juniorYear/DeepLearning/Final_523H0173_523H0178/DL_MedicalVQA_Project/checkpoints/DPO/final_adapter",
+    "/Users/springwang/Library/Mobile Documents/com~apple~CloudDocs/juniorYear/DeepLearning/Final_523H0173_523H0178/DL_MedicalVQA_Project/checkpoints/PPO/final_adapter"
+  ],
+  "weights": [
+    0.4,
+    0.3,
+    0.3
+  ]
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}