From a85ce5f055d2fdfec4155b49e59f3c9ee929300f Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Wed, 15 Nov 2023 16:13:36 -0800
Subject: [PATCH] Add more info messages for truncation / instruction template

---
 extensions/openai/models.py | 5 +++++
 extensions/openai/script.py | 2 +-
 modules/models.py           | 2 +-
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/extensions/openai/models.py b/extensions/openai/models.py
index c0a4606c..1ff950a2 100644
--- a/extensions/openai/models.py
+++ b/extensions/openai/models.py
@@ -1,4 +1,5 @@
 from modules import shared
+from modules.logging_colors import logger
 from modules.models import load_model, unload_model
 from modules.models_settings import get_model_metadata, update_model_parameters
 from modules.utils import get_available_models
@@ -62,3 +63,7 @@ def _load_model(data):
         for k in settings:
             if k in shared.settings:
                 shared.settings[k] = settings[k]
+                if k == 'truncation_length':
+                    logger.info(f"TRUNCATION LENGTH (UPDATED): {shared.settings['truncation_length']}")
+                elif k == 'instruction_template':
+                    logger.info(f"INSTRUCTION TEMPLATE (UPDATED): {shared.settings['instruction_template']}")
diff --git a/extensions/openai/script.py b/extensions/openai/script.py
index ec0ceeef..c7f61abe 100644
--- a/extensions/openai/script.py
+++ b/extensions/openai/script.py
@@ -287,7 +287,7 @@ async def handle_load_model(request_data: LoadModelRequest):
 
 
 @app.post("/v1/internal/model/unload")
-async def handle_load_model():
+async def handle_unload_model():
     unload_model()
     return JSONResponse(content="OK")
 
diff --git a/modules/models.py b/modules/models.py
index de21c8b3..e4c3ddaa 100644
--- a/modules/models.py
+++ b/modules/models.py
@@ -102,7 +102,7 @@ def load_model(model_name, loader=None):
     elif loader in ['llama.cpp', 'llamacpp_HF', 'ctransformers']:
         shared.settings['truncation_length'] = shared.args.n_ctx
 
-    logger.info(f"CONTEXT LENGTH: {shared.settings['truncation_length']}")
+    logger.info(f"TRUNCATION LENGTH: {shared.settings['truncation_length']}")
     logger.info(f"INSTRUCTION TEMPLATE: {shared.settings['instruction_template']}")
     logger.info(f"Loaded the model in {(time.time()-t0):.2f} seconds.")
     return model, tokenizer