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: 128 No newline at end of file test_size: 1 No newline at end of file scripts/exps/prompting/frozenlake/model_config.yaml +11 −5 Original line number Diff line number Diff line Loading @@ -7,6 +7,12 @@ models: # tensor_parallel_size: 2 # gpu_memory_utilization: 0.9 qwen_vl_3b_api: provider: routerapi model_name: qwen/qwen2.5-vl-3b-instruct:free max_tokens: 150 temperature: 0.7 # gpt4o: # provider: openai # model_name: gpt-4o Loading Loading @@ -51,10 +57,10 @@ models: # 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 # 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 scripts/exps/prompting/sokoban/model_config.yaml +14 −14 Original line number Diff line number Diff line Loading @@ -7,21 +7,21 @@ models: # tensor_parallel_size: 2 # gpu_memory_utilization: 0.9 # gpt4o: # provider: openai # model_name: gpt-4o # max_tokens: 150 # temperature: 0.7 # presence_penalty: 0.0 # frequency_penalty: 0.0 # max_retries: 3 # timeout: 60 gpt4o: provider: openai model_name: gpt-4o max_tokens: 150 temperature: 0.7 presence_penalty: 0.0 frequency_penalty: 0.0 max_retries: 3 timeout: 60 # claude_3_sonnet: # provider: claude # model_name: claude-3-7-sonnet-20250219 # max_tokens: 150 # temperature: 0.7 claude_3_sonnet: provider: claude model_name: claude-3-7-sonnet-20250219 max_tokens: 150 temperature: 0.7 # Gemini_2.5_flask: # provider: gemini Loading vagen/mllm_agent/model_interface/__init__.py +5 −0 Original line number Diff line number Diff line Loading @@ -2,6 +2,7 @@ from .vllm import VLLMModelInterface, VLLMModelConfig from .openai import OpenAIModelInterface, OpenAIModelConfig from .claude import ClaudeModelInterface, ClaudeModelConfig from .gemini import GeminiModelInterface, GeminiModelConfig from .routerapi import RouterAPIModelInterface, RouterAPIModelConfig REGISTERED_MODEL = { "vllm": { Loading @@ -19,5 +20,9 @@ REGISTERED_MODEL = { "gemini": { "model_cls": GeminiModelInterface, "config_cls": GeminiModelConfig }, "routerapi": { "model_cls": RouterAPIModelInterface, "config_cls": RouterAPIModelConfig } } No newline at end of file vagen/mllm_agent/model_interface/routerapi/__init__.py 0 → 100644 +2 −0 Original line number Diff line number Diff line from .model import RouterAPIModelInterface from .model_config import RouterAPIModelConfig 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: 128 No newline at end of file test_size: 1 No newline at end of file
scripts/exps/prompting/frozenlake/model_config.yaml +11 −5 Original line number Diff line number Diff line Loading @@ -7,6 +7,12 @@ models: # tensor_parallel_size: 2 # gpu_memory_utilization: 0.9 qwen_vl_3b_api: provider: routerapi model_name: qwen/qwen2.5-vl-3b-instruct:free max_tokens: 150 temperature: 0.7 # gpt4o: # provider: openai # model_name: gpt-4o Loading Loading @@ -51,10 +57,10 @@ models: # 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 # 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
scripts/exps/prompting/sokoban/model_config.yaml +14 −14 Original line number Diff line number Diff line Loading @@ -7,21 +7,21 @@ models: # tensor_parallel_size: 2 # gpu_memory_utilization: 0.9 # gpt4o: # provider: openai # model_name: gpt-4o # max_tokens: 150 # temperature: 0.7 # presence_penalty: 0.0 # frequency_penalty: 0.0 # max_retries: 3 # timeout: 60 gpt4o: provider: openai model_name: gpt-4o max_tokens: 150 temperature: 0.7 presence_penalty: 0.0 frequency_penalty: 0.0 max_retries: 3 timeout: 60 # claude_3_sonnet: # provider: claude # model_name: claude-3-7-sonnet-20250219 # max_tokens: 150 # temperature: 0.7 claude_3_sonnet: provider: claude model_name: claude-3-7-sonnet-20250219 max_tokens: 150 temperature: 0.7 # Gemini_2.5_flask: # provider: gemini Loading
vagen/mllm_agent/model_interface/__init__.py +5 −0 Original line number Diff line number Diff line Loading @@ -2,6 +2,7 @@ from .vllm import VLLMModelInterface, VLLMModelConfig from .openai import OpenAIModelInterface, OpenAIModelConfig from .claude import ClaudeModelInterface, ClaudeModelConfig from .gemini import GeminiModelInterface, GeminiModelConfig from .routerapi import RouterAPIModelInterface, RouterAPIModelConfig REGISTERED_MODEL = { "vllm": { Loading @@ -19,5 +20,9 @@ REGISTERED_MODEL = { "gemini": { "model_cls": GeminiModelInterface, "config_cls": GeminiModelConfig }, "routerapi": { "model_cls": RouterAPIModelInterface, "config_cls": RouterAPIModelConfig } } No newline at end of file
vagen/mllm_agent/model_interface/routerapi/__init__.py 0 → 100644 +2 −0 Original line number Diff line number Diff line from .model import RouterAPIModelInterface from .model_config import RouterAPIModelConfig No newline at end of file
