llm: Set n by default in gen_kwargs

Prior to converting to yaml format, we were setting `n` to the value
of `num_instructions_to_generate`. It was dropped from the yaml since
it's a runtime configuration value. We need to set it here so it's set
like it was before.

Co-authored-by: Mark McLoughlin <[email protected]>
Signed-off-by: Russell Bryant <[email protected]>

src/instructlab/sdg/llmblock.py

@@ -78,6 +78,7 @@ def __init__(
             "model": self.ctx.model_id,
             "temperature": 0,
             "max_tokens": 12000,
+            "n": self.ctx.num_instructions_to_generate,
         }
 
         # Whether the LLM server supports a list of input prompts