Loading scripts/exps/prompting/frozenlake/free_think/env_config.yaml +1 −1 Original line number Diff line number Diff line Loading @@ -5,4 +5,4 @@ env1: use_accuracy_reward: false prompt_format: free_think train_size: 10000 test_size: 512 No newline at end of file test_size: 128 No newline at end of file scripts/exps/prompting/frozenlake/grounding/env_config.yaml +1 −1 Original line number Diff line number Diff line Loading @@ -5,4 +5,4 @@ env1: prompt_format: grounding use_accuracy_reward: false train_size: 10000 test_size: 512 No newline at end of file test_size: 128 No newline at end of file scripts/exps/prompting/frozenlake/grounding_worldmodeling/env_config.yaml +1 −1 Original line number Diff line number Diff line Loading @@ -5,4 +5,4 @@ env1: prompt_format: grounding_worldmodeling use_accuracy_reward: false train_size: 10000 test_size: 512 No newline at end of file test_size: 128 No newline at end of file scripts/exps/prompting/frozenlake/inference_config.yaml +1 −1 Original line number Diff line number Diff line Loading @@ -15,7 +15,7 @@ output_dir: "inference_outputs" # WandB configuration use_wandb: true wandb_project: "vagen-inference" val_generations_to_log_to_wandb: 10 val_generations_to_log_to_wandb: 64 # Display settings show_progress: true scripts/exps/prompting/frozenlake/model_config.yaml +11 −11 Original line number Diff line number Diff line Loading @@ -7,6 +7,12 @@ models: # tensor_parallel_size: 2 # gpu_memory_utilization: 0.9 # VLM-R1-MATH: # provider: vllm # model_name: omlab/VLM-R1-Qwen2.5VL-3B-Math-0305 # max_tokens: 150 # temperature: 0.7 # gpt4o: # provider: openai # model_name: gpt-4o Loading Loading @@ -39,22 +45,16 @@ models: # batch_poll_interval: 10 # Poll every 10 seconds # batch_max_wait_time: 7200 # Wait up to 2 hours # VLM-R1-MATH: # VLM-R1-OVD: # provider: vllm # model_name: omlab/VLM-R1-Qwen2.5VL-3B-Math-0305 # model_name: omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321 # max_tokens: 150 # temperature: 0.7 # VLM-R1-OVD: # VLM-R1-REC: # provider: vllm # model_name: omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321 # model_name: omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps # max_tokens: 150 # temperature: 0.7 VLM-R1-REC: provider: vllm model_name: omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps max_tokens: 150 temperature: 0.7 No newline at end of file Loading
scripts/exps/prompting/frozenlake/free_think/env_config.yaml +1 −1 Original line number Diff line number Diff line Loading @@ -5,4 +5,4 @@ env1: use_accuracy_reward: false prompt_format: free_think train_size: 10000 test_size: 512 No newline at end of file test_size: 128 No newline at end of file
scripts/exps/prompting/frozenlake/grounding/env_config.yaml +1 −1 Original line number Diff line number Diff line Loading @@ -5,4 +5,4 @@ env1: prompt_format: grounding use_accuracy_reward: false train_size: 10000 test_size: 512 No newline at end of file test_size: 128 No newline at end of file
scripts/exps/prompting/frozenlake/grounding_worldmodeling/env_config.yaml +1 −1 Original line number Diff line number Diff line Loading @@ -5,4 +5,4 @@ env1: prompt_format: grounding_worldmodeling use_accuracy_reward: false train_size: 10000 test_size: 512 No newline at end of file test_size: 128 No newline at end of file
scripts/exps/prompting/frozenlake/inference_config.yaml +1 −1 Original line number Diff line number Diff line Loading @@ -15,7 +15,7 @@ output_dir: "inference_outputs" # WandB configuration use_wandb: true wandb_project: "vagen-inference" val_generations_to_log_to_wandb: 10 val_generations_to_log_to_wandb: 64 # Display settings show_progress: true
scripts/exps/prompting/frozenlake/model_config.yaml +11 −11 Original line number Diff line number Diff line Loading @@ -7,6 +7,12 @@ models: # tensor_parallel_size: 2 # gpu_memory_utilization: 0.9 # VLM-R1-MATH: # provider: vllm # model_name: omlab/VLM-R1-Qwen2.5VL-3B-Math-0305 # max_tokens: 150 # temperature: 0.7 # gpt4o: # provider: openai # model_name: gpt-4o Loading Loading @@ -39,22 +45,16 @@ models: # batch_poll_interval: 10 # Poll every 10 seconds # batch_max_wait_time: 7200 # Wait up to 2 hours # VLM-R1-MATH: # VLM-R1-OVD: # provider: vllm # model_name: omlab/VLM-R1-Qwen2.5VL-3B-Math-0305 # model_name: omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321 # max_tokens: 150 # temperature: 0.7 # VLM-R1-OVD: # VLM-R1-REC: # provider: vllm # model_name: omlab/VLM-R1-Qwen2.5VL-3B-OVD-0321 # model_name: omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps # max_tokens: 150 # temperature: 0.7 VLM-R1-REC: provider: vllm model_name: omlab/Qwen2.5VL-3B-VLM-R1-REC-500steps max_tokens: 150 temperature: 0.7 No newline at end of file
