dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-28 16:25:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

refactor: Update Ollama model detection and context window documentation

Browse source
This commit is contained in:
Paul Gauthier 2024-11-24 16:14:34 -08:00 • committed by Paul Gauthier (aider)
parent 7d14d4ade9
commit 325cdfcf57
3 changed files with 16 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

2
aider/models.py
View file

@ -938,7 +938,7 @@ class Model(ModelSettings):
self.edit_format = "diff"
self.editor_edit_format = "editor-diff"
self.use_repo_map = True
if "ollama" in model:
if model.startswith("ollama/") or model.startswith("ollama_chat/"):
self.extra_params = dict(num_ctx=8 * 1024)
return # <--

11
aider/website/_posts/2024-11-21-quantization.md
View file

@ -116,19 +116,12 @@ in the chat to make it fit within the context window.
All of the Ollama results above were collected with at least an 8k context window, which
is large enough to attempt all the coding problems in the benchmark.
Aider sets Ollama's context window to 8k by default.
You can set the Ollama server's context window with a
You can change the Ollama server's context window with a
[`.aider.model.settings.yml` file](https://aider.chat/docs/config/adv-model-settings.html#model-settings)
like this:
```
- name: aider/extra_params
extra_params:
num_ctx: 8192
```
That uses the special model name `aider/extra_params` to set it for *all* models. You should probably use a specific model name like:
```
- name: ollama/qwen2.5-coder:32b-instruct-fp16
extra_params:

29
aider/website/docs/llms/ollama.md
View file

@ -44,28 +44,25 @@ setx OLLAMA_API_KEY <api-key> # Windows, restart shell after setx
[Ollama uses a 2k context window by default](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size),
which is very small for working with aider.
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.
All of the Ollama results above were collected with at least an 8k context window, which
is large enough to attempt all the coding problems in the benchmark.
You can set the Ollama server's context window with a
Aider sets Ollama's context window to 8k by default.
If you would like
a large context window
you can use a
[`.aider.model.settings.yml` file](https://aider.chat/docs/config/adv-model-settings.html#model-settings)
like this:
```
- name: aider/extra_params
extra_params:
num_ctx: 8192
```
That uses the special model name `aider/extra_params` to set it for *all* models. You should probably use a specific model name like:
```
- name: ollama/qwen2.5-coder:32b-instruct-fp16
extra_params:
num_ctx: 8192
```
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.
So if your context window is too small, you won't get an error.
Aider will probably just fail to work well and experience
a lot of
[file editing problems](https://aider.chat/docs/troubleshooting/edit-errors.html).