Update llm_inference.py

llm_inference.py

@@ -184,7 +184,7 @@ Your output is only the caption itself, no comments or extra formatting. The cap
                 response = self.huggingface_client.chat.completions.create(
                     model=model or "meta-llama/Meta-Llama-3.1-70B-Instruct",
                     max_tokens=1024,
-                    temperature=0.7,
+                    temperature=1.0,
                     top_p=0.95,
                     messages=[
                         {"role": "system", "content": system_message},
@@ -198,7 +198,7 @@ Your output is only the caption itself, no comments or extra formatting. The cap
                 response = self.groq_client.chat.completions.create(
                     model=model or "llama-3.1-70b-versatile",
                     max_tokens=1024,
-                    temperature=0.7,
+                    temperature=1.0,
                     messages=[
                         {"role": "system", "content": system_message},
                         {"role": "user", "content": user_message},
@@ -211,7 +211,7 @@ Your output is only the caption itself, no comments or extra formatting. The cap
                 response = self.sambanova_client.chat.completions.create(
                     model=model or "Meta-Llama-3.1-70B-Instruct",
                     max_tokens=1024,
-                    temperature=0.7,
+                    temperature=1.0,
                     messages=[
                         {"role": "system", "content": system_message},
                         {"role": "user", "content": user_message},