From f1c631dc533706ed3caffe19b3c944f1665e62a4 Mon Sep 17 00:00:00 2001
From: Daniele Morotti <58258368+DanieleMorotti@users.noreply.github.com>
Date: Sun, 17 Dec 2023 00:59:50 +0100
Subject: [PATCH] Bug fixed with n_ctx=0 (#1015)

If the n_ctx is set to 0 the code should use the maximum context length of the selected model, but it didn't work. There was a problem with the initialization of this parameter and a related problem with 'n_batch'.
---
 llama_cpp/llama.py | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/llama_cpp/llama.py b/llama_cpp/llama.py
index d5cf401..15307ab 100644
--- a/llama_cpp/llama.py
+++ b/llama_cpp/llama.py
@@ -923,6 +923,12 @@ class Llama:
         self._model = _LlamaModel(
             path_model=self.model_path, params=self.model_params, verbose=self.verbose
         )
+        # Set the default value for the context and correct the batch
+        if n_ctx == 0:
+            n_ctx = self._model.n_ctx_train()
+            self.n_batch = min(n_ctx, n_batch)
+            self.context_params.n_ctx = self._model.n_ctx_train()
+            self.context_params.n_batch = self.n_batch
 
         self._ctx = _LlamaContext(
             model=self._model,