matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 00:37:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revert "increase default context length to 4096 (#10364)"

Browse Source 
This reverts commit 424f648632.
This commit is contained in:
Devon Rifkin
2025-04-28 16:54:11 -07:00
committed by GitHub
parent 5cfc1c39f3
commit dd93e1af85
7 changed files with 12 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/faq.md
View File

@@ -20,7 +20,7 @@ Please refer to the [GPU docs](./gpu.md).
## How can I specify the context window size?
By default, Ollama uses a context window size of 4096 tokens, unless you have a single GPU with <= 4 GB of VRAM, in which case it will default to 2048 tokens.
By default, Ollama uses a context window size of 2048 tokens.
This can be overridden with the `OLLAMA_CONTEXT_LENGTH` environment variable. For example, to set the default context window to 8K, use:
@@ -31,7 +31,7 @@ OLLAMA_CONTEXT_LENGTH=8192 ollama serve
To change this when using `ollama run`, use `/set parameter`:
```shell
/set parameter num_ctx 8192
/set parameter num_ctx 4096
```
When using the API, specify the `num_ctx` parameter:
@@ -41,7 +41,7 @@ curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"options": {
"num_ctx": 8192
"num_ctx": 4096
}
}'
```