dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-02 02:34:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

copy

Browse source
This commit is contained in:
Paul Gauthier 2025-01-28 11:22:09 -08:00
parent 0b5e0a1113
commit 3422718415
2 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
aider/website/_posts/2025-01-28-deepseek-down.md
View file

@ -119,8 +119,11 @@ setx OLLAMA_API_BASE http://127.0.0.1:11434 # Windows, restart shell after set
aider --model ollama/deepseek-v3 aider --model ollama/deepseek-v3
``` ```
It's important to provide model settings, especially the `num_ctx` parameter. It's important to provide model settings, especially the `num_ctx` parameter to
set the context window.
Ollama uses a 2k context window by default, which is very small for working with aider. Ollama uses a 2k context window by default, which is very small for working with aider.
Larger context windows will allow you to work with larger amounts of code,
but will use memory and increase latency.
Unlike most other LLM servers, Ollama does not throw an error if you submit a request that exceeds the context window. Instead, it just silently truncates the request by discarding the “oldest” messages in the chat to make it fit within the context window. Unlike most other LLM servers, Ollama does not throw an error if you submit a request that exceeds the context window. Instead, it just silently truncates the request by discarding the “oldest” messages in the chat to make it fit within the context window.
@ -137,15 +140,13 @@ Create a `.aider.model.settings.yml` file in your home directory or git project
lazy: false lazy: false
reminder: sys reminder: sys
examples_as_sys_msg: true examples_as_sys_msg: true
extra_params:
max_tokens: 8192
cache_control: false cache_control: false
caches_by_default: true caches_by_default: true
use_system_prompt: true use_system_prompt: true
use_temperature: true use_temperature: true
streaming: true streaming: true
extra_params: extra_params:
num_ctx: 8192 num_ctx: 8192 # How large a context window?
``` ```
## Other providers ## Other providers

2
aider/website/docs/llms/ollama.md
View file

@ -56,6 +56,8 @@ you added to the chat.
That's because ollama is silently discarding them because they exceed the context window. That's because ollama is silently discarding them because they exceed the context window.
Aider sets Ollama's context window to 8k by default. Aider sets Ollama's context window to 8k by default.
Larger context windows will allow you to work with larger amounts of code,
but will use memory and increase latency.
If you would like If you would like
a larger context window a larger context window
you can use a you can use a