Originally created by @matbeedotcom on GitHub (Jun 4, 2024).
Is your feature request related to a problem? Please describe.
Yes, once the maximum context window is reached, it fails by sending the entire context to the llm api.
Describe the solution you'd like
Support a variety of context clipping mechanisms
I'm trying to use Exllamav2 models as Ollama is far too slow with LLaMa3-70b
Originally created by @matbeedotcom on GitHub (Jun 4, 2024).
**Is your feature request related to a problem? Please describe.**
Yes, once the maximum context window is reached, it fails by sending the entire context to the llm api.
**Describe the solution you'd like**
Support a variety of context clipping mechanisms
I'm trying to use Exllamav2 models as Ollama is far too slow with LLaMa3-70b
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @matbeedotcom on GitHub (Jun 4, 2024).
Is your feature request related to a problem? Please describe.
Yes, once the maximum context window is reached, it fails by sending the entire context to the llm api.
Describe the solution you'd like
Support a variety of context clipping mechanisms
I'm trying to use Exllamav2 models as Ollama is far too slow with LLaMa3-70b
@tjbck commented on GitHub (Jun 4, 2024):
#1268