github/home-llm
1
1
Fork 0
mirror of https://github.com/acon96/home-llm.git synced 2026-01-08 21:28:05 -05:00
Code Issues Packages Projects Releases Wiki Activity

better handling for llama.cpp context size errors

Browse Source
This commit is contained in:
Alex O'Connell
2024-08-21 11:47:52 -04:00
parent 011d5a0b0d
commit 9cdfffc530
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
custom_components/llama_conversation/conversation.py
View File

@@ -1165,6 +1165,11 @@ class LlamaCppAgent(LocalLLMAgent):
)
context_len = self.entry.options.get(CONF_CONTEXT_LENGTH, DEFAULT_CONTEXT_LENGTH)
if len(input_tokens) >= context_len:
num_entities = len(self._async_get_exposed_entities()[0])
context_size = self.entry.options.get(CONF_CONTEXT_LENGTH, DEFAULT_CONTEXT_LENGTH)
self._warn_context_size()
raise Exception(f"The model failed to produce a result because too many devices are exposed ({num_entities} devices) for the context size ({context_size} tokens)!")
if len(input_tokens) + max_tokens >= context_len:
self._warn_context_size()