Specify absolute path

PrepareVicuna.md

@@ -28,7 +28,7 @@ pip install git+https://github.com/lm-sys/[email protected]
 Then, run the following command to create the final working weight
 
 ```
-python -m fastchat.model.apply_delta --base /path/to/llama-13bOR7b-hf/  --target /path/to/save/working/vicuna/weight/  --delta /path/to/vicuna-13bOR7b-delta-v0/
+python -m fastchat.model.apply_delta --base /absolute/path/to/llama-13bOR7b-hf/  --target /absolute/path/to/save/working/vicuna/weight/  --delta /absolute/path/to/vicuna-13bOR7b-delta-v0/
 ```
 
 Now you are good to go!

README.md

@@ -64,9 +64,9 @@ Download the corresponding LLM weights from the following huggingface space via
  [Downlad](https://huggingface.co/Vision-CAIR/vicuna/tree/main) | [Download](https://huggingface.co/Vision-CAIR/vicuna-7b/tree/main) | [Download](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf/tree/main)
 
 
-Then, set the path to the vicuna weight in the model config file 
+Then, set the absolute path to the vicuna weight in the model config file 
 [here](minigpt4/configs/models/minigpt4_vicuna0.yaml#L18) at Line 18
-and/or the path to the llama2 weight in the model config file 
+and/or the absolute path to the llama2 weight in the model config file 
 [here](minigpt4/configs/models/minigpt4_llama2.yaml#L15) at Line 15.
 
 **3. Prepare the pretrained MiniGPT-4 checkpoint**
@@ -78,7 +78,7 @@ Download the pretrained checkpoints according to the Vicuna model you prepare.
  [Downlad](https://drive.google.com/file/d/1a4zLvaiDBr-36pasffmgpvH5P7CKmpze/view?usp=share_link) | [Download](https://drive.google.com/file/d/1RY9jV0dyqLX-o38LrumkKRh6Jtaop58R/view?usp=sharing)  | [Download](https://drive.google.com/file/d/11nAPjEok8eAGGEG1N2vXo3kBLCg0WgUk/view?usp=sharing) 
 
 
-Then, set the path to the pretrained checkpoint in the evaluation config file 
+Then, set the absolute path to the pretrained checkpoint in the evaluation config file 
 in [eval_configs/minigpt4_eval.yaml](eval_configs/minigpt4_eval.yaml#L10) at Line 8 for Vicuna version or [eval_configs/minigpt4_llama2_eval.yaml](eval_configs/minigpt4_llama2_eval.yaml#L10) for LLama2 version.   
 
 
@@ -118,7 +118,7 @@ our [first stage dataset preparation instruction](dataset/README_1_STAGE.md).
 After the first stage, the visual features are mapped and can be understood by the language
 model.
 To launch the first stage training, run the following command. In our experiments, we use 4 A100. 
-You can change the save path in the config file 
+You can change the relative save path in the config file 
 [train_configs/minigpt4_stage1_pretrain.yaml](train_configs/minigpt4_stage1_pretrain.yaml)
 
 ```bash
@@ -137,9 +137,9 @@ and convert it to a conversation format to further align MiniGPT-4.
 To download and prepare our second stage dataset, please check our 
 [second stage dataset preparation instruction](dataset/README_2_STAGE.md).
 To launch the second stage alignment, 
-first specify the path to the checkpoint file trained in stage 1 in 
+first specify the absolute path to the checkpoint file trained in stage 1 in 
 [train_configs/minigpt4_stage1_pretrain.yaml](train_configs/minigpt4_stage2_finetune.yaml).
-You can also specify the output path there. 
+You can also specify the relative output path there. 
 Then, run the following command. In our experiments, we use 1 A100.
 
 ```bash

dataset/README_1_STAGE.md

@@ -21,7 +21,7 @@ laion_synthetic_filtered_large.json
 
 ### setup the dataset folder and move the annotation file to the data storage folder
 ```
-export MINIGPT4_DATASET=/YOUR/PATH/FOR/LARGE/DATASET/
+export MINIGPT4_DATASET=/YOUR/ABSOLUTE/PATH/FOR/LARGE/DATASET/
 mkdir ${MINIGPT4_DATASET}/cc_sbu
 mkdir ${MINIGPT4_DATASET}/laion
 mv ccs_synthetic_filtered_large.json ${MINIGPT4_DATASET}/cc_sbu
@@ -84,11 +84,11 @@ The final dataset structure
 
 ## Set up the dataset configuration files
 
-Then, set up the LAION dataset loading path in 
+Then, set up the absolute LAION dataset loading path in 
 [here](../minigpt4/configs/datasets/laion/defaults.yaml#L5) at Line 5 as 
 ${MINIGPT4_DATASET}/laion/laion_dataset/{00000..10488}.tar
 
-and the Conceptual Captoin and SBU datasets loading path in 
+and the absolute Conceptual Captoin and SBU datasets loading path in 
 [here](../minigpt4/configs/datasets/cc_sbu/defaults.yaml#L5) at Line 5 as 
 ${MINIGPT4_DATASET}/cc_sbu/cc_sbu_dataset/{00000..01255}.tar
 

dataset/README_2_STAGE.md

@@ -14,6 +14,6 @@ cc_sbu_align
 ```
 
 Put the folder to any path you want.
-Then, set up the dataset path in the dataset config file 
+Then, set up the absolute dataset path in the dataset config file 
 [here](../minigpt4/configs/datasets/cc_sbu/align.yaml#L5) at Line 5.
 

eval_configs/minigpt4_llama2_eval.yaml

@@ -5,7 +5,7 @@ model:
   end_sym: "</s>"
   low_resource: True
   prompt_template: '[INST] {} [/INST] '
-  ckpt: '/path/to/checkpoint/'
+  ckpt: '/absolute/path/to/checkpoint/'
 
 
 datasets:

minigpt4/configs/datasets/cc_sbu/align.yaml

@@ -2,4 +2,4 @@ datasets:
   cc_sbu_align:
     data_type: images
     build_info:
-      storage: /path/to/cc_sbu_align/
+      storage: /absolute/path/to/cc_sbu_align/

minigpt4/configs/datasets/cc_sbu/defaults.yaml

@@ -2,4 +2,4 @@ datasets:
   cc_sbu:
     data_type: images
     build_info:
-      storage: /path/to/cc_sbu_dataset/{00000..01255}.tar
+      storage: /absolute/path/to/cc_sbu_dataset/{00000..01255}.tar

minigpt4/configs/datasets/laion/defaults.yaml

@@ -2,4 +2,4 @@ datasets:
   laion:
     data_type: images
     build_info:
-      storage: /path/to/laion_dataset/{00000..10488}.tar
+      storage: /absolute/path/to/laion_dataset/{00000..10488}.tar

minigpt4/configs/models/minigpt4_llama2.yaml

@@ -12,7 +12,7 @@ model:
   # generation configs
   prompt: ""
 
-  llama_model: "/path/to/llama2/weight"
+  llama_model: "/absolute/path/to/llama2/weight"
 
 preprocess:
     vis_processor:

minigpt4/configs/models/minigpt4_vicuna0.yaml

@@ -15,7 +15,7 @@ model:
   # generation configs
   prompt: ""
 
-  llama_model: "/path/to/vicuna/weight"
+  llama_model: "/absolute/path/to/vicuna/weight"
 
 preprocess:
     vis_processor:

train_configs/minigpt4_llama2_stage2_finetune.yaml

@@ -6,7 +6,7 @@ model:
   end_sym: "</s>"
   prompt_path: "prompts/alignment.txt"
   prompt_template: '[INST] {} [/INST] '
-  ckpt: '/path/to/stage1/checkpoint/'
+  ckpt: '/absolute/path/to/stage1/checkpoint/'
 
 
 datasets:

train_configs/minigpt4_stage2_finetune.yaml

@@ -6,7 +6,7 @@ model:
   end_sym: "###"
   prompt_path: "prompts/alignment.txt"
   prompt_template: '###Human: {} ###Assistant: '
-  ckpt: '/path/to/stage1/checkpoint/'
+  ckpt: '/absolute/path/to/stage1/checkpoint/'
 
 
 datasets: