Fix inaccurate Ollama context length for qwen2.5 models (#20933)

Peter Tripp and Patrick Samson created 

Since Ollama/llama.cpp do not currently YARN for context length
extension, the context length is limited to `32768`. This can be
confirmed by the Ollama model card.
See corresponding issue on Ollama repo : 
https://github.com/ollama/ollama/issues/6865

Co-authored-by: Patrick Samson <1416027+patricksamson@users.noreply.github.com>

Change summary

crates/ollama/src/ollama.rs | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)

Detailed changes

crates/ollama/src/ollama.rs 🔗 

@@ -81,9 +81,10 @@ fn get_max_tokens(name: &str) -> usize {
         "llama2" | "yi" | "vicuna" | "stablelm2" => 4096,
         "llama3" | "gemma2" | "gemma" | "codegemma" | "starcoder" | "aya" => 8192,
         "codellama" | "starcoder2" => 16384,
-        "mistral" | "codestral" | "mixstral" | "llava" | "qwen2" | "dolphin-mixtral" => 32768,
+        "mistral" | "codestral" | "mixstral" | "llava" | "qwen2" | "qwen2.5-coder"
+        | "dolphin-mixtral" => 32768,
         "llama3.1" | "phi3" | "phi3.5" | "command-r" | "deepseek-coder-v2" | "yi-coder"
-        | "llama3.2" | "qwen2.5-coder" => 128000,
+        | "llama3.2" => 128000,
         _ => DEFAULT_TOKENS,
     }
     .clamp(1, MAXIMUM_TOKENS)