mcp-sentiment / .continue /models /local-models.yaml
faizan-shaikh's picture
Tested LLM on local via Llama cpp and added a mcp server
40940e1
raw
history blame contribute delete
314 Bytes
name: Llama.cpp model
version: 0.0.1
schema: v1
models:
- provider: llama.cpp
model: unsloth/Devstral-Small-2505-GGUF
apiBase: http://localhost:8080
defaultCompletionOptions:
contextLength: 8192 # Adjust based on the model
name: Llama.cpp Devstral-Small
roles:
- chat
- edit