Merge pull request #97 from Deep-Agent/v0.1.0

V0.1.0
Deep-Agent · Feb 14, 2025 · 1879105 · 1879105
2 parents 80216dc + b97379a
commit 1879105
Show file tree

Hide file tree

Showing 36 changed files with 15 additions and 461 deletions.
diff --git a/README.md b/README.md
@@ -72,6 +72,9 @@
 ## Setup
 
 ```bash
+conda create -n r1-v python=3.11 
+conda activate r1-v
+
 bash setup.sh
 ```
 
@@ -99,7 +102,7 @@ bash setup.sh
 ### GRPO
 
 ```bash
-cd src/open-r1-multimodal
+cd src/r1-v
 
 export DEBUG_MODE="true" # Enable Debug if you want to see the rollout of model during RL
 export LOG_PATH="./debug_log_2b.txt"
@@ -143,7 +146,7 @@ torchrun --nproc_per_node="8" \
 We also provide SFT code, please follow the script and edit the config to customize the sft task.
 
 ```bash
-accelerate launch --config_file src/open-r1-multimodal/configs/zero2.yaml src/open-r1-multimodal/src/open_r1/sft.py --config src/open-r1-multimodal/configs/qwen2vl_sft_config.yaml 
+accelerate launch --config_file src/r1-v/configs/zero2.yaml src/r1-v/src/open_r1/sft.py --config src/r1-v/configs/qwen2vl_sft_config.yaml 
 ```
 
 ## Evaluation

diff --git a/setup.sh b/setup.sh
@@ -1,8 +1,5 @@
-conda create -n r1-v python=3.11 
-conda activate r1-v
-
-# Install the packages in open-r1-multimodal .
-cd src/open-r1-multimodal # We edit the grpo.py and grpo_trainer.py in open-r1 repo.
+# Install the packages in r1-v .
+cd src/r1-v 
 pip install -e ".[dev]"
 
 # Addtional modules
@@ -11,7 +8,7 @@ pip install tensorboardx
 pip install qwen_vl_utils torchvision
 pip install flash-attn --no-build-isolation
 
-# vLLM support
+# vLLM support 
 pip install vllm==0.7.2
 
 # fix transformers version

diff --git a/src/open-r1-multimodal/README.md b/src/open-r1-multimodal/README.md
diff --git a/src/open-r1-multimodal/assets/lmm_r1.png b/src/open-r1-multimodal/assets/lmm_r1.png
diff --git a/src/open-r1-multimodal/assets/plan-of-attack.png b/src/open-r1-multimodal/assets/plan-of-attack.png
diff --git a/src/open-r1-multimodal/slurm/evaluate.slurm b/src/open-r1-multimodal/slurm/evaluate.slurm