branch: externals/minuet
commit 5e4a43cd0d216766d8dc3e6c27d7e30be14e52c2
Author: Milan Glacier <[email protected]>
Commit: Milan Glacier <[email protected]>
doc: fix TOC.
---
recipes.md | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/recipes.md b/recipes.md
index 4646431bd7..f1717fa31a 100644
--- a/recipes.md
+++ b/recipes.md
@@ -1,9 +1,9 @@
-- [Launching the llama.cpp Server: Example
Script](#launching-the-llamacpp-server-example-script) +
- [**For Systems with More Than 16GB
VRAM**](#for-systems-with-more-than-16gb-vram) +
- [**For Systems with Less Than 16GB
VRAM**](#for-systems-with-less-than-16gb-vram) +
- [**For Systems with Less Than 8GB
VRAM**](#for-systems-with-less-than-8gb-vram)
+- [Launching the llama.cpp Server: Example
Script](#launching-the-llamacpp-server-example-script)
+ - [For Systems with More Than 16GB
VRAM](#for-systems-with-more-than-16gb-vram)
+ - [For Systems with Less Than 16GB
VRAM](#for-systems-with-less-than-16gb-vram)
+ - [For Systems with Less Than 8GB VRAM](#for-systems-with-less-than-8gb-vram)
- [Example minuet config](#example-minuet-config)
- - [**Acknowledgment**](#acknowledgment)
+ - [Acknowledgment](#acknowledgment)
- [Using Non-OpenAI-Compatible FIM APIs with
DeepInfra](#using-non-openai-compatible-fim-apis-with-deepinfra)
- [Using Vertex AI with Gemini Models](#using-vertex-ai-with-gemini-models)
@@ -12,7 +12,7 @@
This guide provides several configuration variants for the `qwen2.5-coder`
based
on local computing power, specifically the available VRAM.
-### **For Systems with More Than 16GB VRAM**
+### For Systems with More Than 16GB VRAM
```bash
llama-server \
@@ -21,7 +21,7 @@ llama-server \
--ctx-size 0 --cache-reuse 256
```
-### **For Systems with Less Than 16GB VRAM**
+### For Systems with Less Than 16GB VRAM
```bash
llama-server \
@@ -30,7 +30,7 @@ llama-server \
--ctx-size 0 --cache-reuse 256
```
-### **For Systems with Less Than 8GB VRAM**
+### For Systems with Less Than 8GB VRAM
```bash
llama-server \
@@ -83,7 +83,7 @@ llama-server \
> Different LLMs use different special tokens during training, so you should
> adjust these tokens according to your preferred LLM.
-## **Acknowledgment**
+## Acknowledgment
- [llama.vim](https://github.com/ggml-org/llama.vim): A reference for CLI
parameters used in launching the `llama.cpp` server.
