Upload README.md

README.md

@@ -14,7 +14,7 @@ It was trained on a custom dataset consisting of scientific chemistry papers fro
 
 The aim with this model was to create a chemistry model that was trained on current data from 2025. Of course, it will be a few months out of date since data processing and dataset creation takes significant time as a solo developer.
 
-> The following sections are either copied as they were from the **Qwen3-4B-Thinking-2507** page or slightly modified. I didn't want to make it seem like I just ripped them off.
+> The following sections are either copied as they were from the **onieth/chemAI2025** page or slightly modified. I didn't want to make it seem like I just ripped them off.
 ## Model Overview
 
 **chemAi2025** has the same model features as **Qwen3-4B-Thinking-2507**. Which are:
@@ -112,9 +112,9 @@ from qwen_agent.agents import Assistant
 # Define LLM
 # Using OpenAI-compatible API endpoint. It is recommended to disable the reasoning and the tool call parsing
 # functionality of the deployment frameworks and let Qwen-Agent automate the related operations. For example, 
-# `VLLM_USE_MODELSCOPE=true vllm serve Qwen/Qwen3-4B-Thinking-2507 --served-model-name Qwen3-4B-Thinking-2507 --max-model-len 262144`.
+# `VLLM_USE_MODELSCOPE=true vllm serve onieth/chemAI2025 --served-model-name onieth/chemAI2025 --max-model-len 262144`.
 llm_cfg = {
-    'model': 'Qwen3-4B-Thinking-2507',
+    'model': 'onieth/chemAI2025',
 
     # Use a custom endpoint compatible with OpenAI API:
     'model_server': 'http://localhost:8000/v1',  # api_base without reasoning and tool call parsing