From 29a4a65e6d2d7b7127006ac9a5938a57206c761f Mon Sep 17 00:00:00 2001 From: Robert Washbourne Date: Mon, 11 Nov 2024 06:16:30 +0000 Subject: [PATCH] s --- mcts/tree_search.py | 2 +- modal_prm_reward.py | 3 ++- modal_vllm.py | 6 ++++-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/mcts/tree_search.py b/mcts/tree_search.py index b3797b1..776aea6 100644 --- a/mcts/tree_search.py +++ b/mcts/tree_search.py @@ -14,7 +14,7 @@ # URLs and configuration # POLICY_URL = 'https://rawsh--vllm-qwen-ft-serve.modal.run/v1/' -POLICY_MODEL_NAME = 'mirrorqwen2.5-0.5b-SimPO-2' +POLICY_MODEL_NAME = 'mirrorqwen2.5-0.5b-SimPO-3' POLICY_URL = 'https://rawsh--vllm-qwen-simpo-serve.modal.run/v1/' PRM_URL = 'https://rawsh--mirrorqwen-prm-embedder-score-output.modal.run' API_KEY = '9FF74944EED19865193F979942FB1' diff --git a/modal_prm_reward.py b/modal_prm_reward.py index 3f87ac6..75c84b3 100644 --- a/modal_prm_reward.py +++ b/modal_prm_reward.py @@ -48,7 +48,8 @@ class Embedder: # revision = "42e07d1b708282ac2aae338050d8116f8c69398d" # st0 # revision = "65f4a7601dffacc40e0ef7fa4733d346c926bd18" # st1 v1 # revision = "80da7ccc4f107e0cb6bf937d61be4702badfb96b" # st1 v2 - revision = "4d618515c90069993f4b32e4201783efdeebbc22" # st2 + # revision = "4d618515c90069993f4b32e4201783efdeebbc22" # st2 + revesion = "b052380b619e5c62ce9f407522362f5caf7b8346" # st3 device = "cuda" print(model_id) diff --git a/modal_vllm.py b/modal_vllm.py index aa7f1b6..d037e05 100644 --- a/modal_vllm.py +++ b/modal_vllm.py @@ -26,8 +26,10 @@ def download_model_to_image(model_dir, model_name, model_revision): # st1 v2 # MODEL_NAME = "rawsh/mirrorqwen2.5-0.5b-SimPO-1" # MODEL_REVISION = "9e6d25903688b5678bdbe333c537a58488212024" -MODEL_NAME = "rawsh/mirrorqwen2.5-0.5b-SimPO-2" -MODEL_REVISION = "a41b6dd0307cf080a83cf20efc25bbf025b47852" +# MODEL_NAME = "rawsh/mirrorqwen2.5-0.5b-SimPO-2" +# MODEL_REVISION = "a41b6dd0307cf080a83cf20efc25bbf025b47852" +MODEL_NAME = "rawsh/mirrorqwen2.5-0.5b-SimPO-3" +MODEL_REVISION = "4bf9608e31850cf1020de695d99f0c1fb9e0575f" vllm_image = ( modal.Image.debian_slim(python_version="3.10")