Update Build

sirajperson · sirajperson · commit af336a94a058 · 2023-07-05T16:29:27.000-04:00
diff --git a/.gitmodules b/.gitmodules
@@ -1,6 +1,3 @@
-[submodule "vendor/llama.cpp"]
-	path = vendor/llama.cpp
-	url = https://github.com/ggerganov/llama.cpp.git
 [submodule "ggllm.cpp"]
 	path = ggllm.cpp
 	url = https://github.com/cmp-nct/ggllm.cpp
diff --git a/Makefile b/Makefile
@@ -34,14 +34,14 @@ deploy.gh-docs:
 	mkdocs gh-deploy
 
 clean:
-	- cd vendor/llama.cpp && make clean
-	- cd vendor/llama.cpp && rm libllama.so
+	- cd vendor/ggllm.cpp && make clean
+	- cd vendor/ggllm.cpp && rm ggllm.so
 	- rm -rf _skbuild
-	- rm llama_cpp/*.so
-	- rm llama_cpp/*.dylib
-	- rm llama_cpp/*.metal
-	- rm llama_cpp/*.dll
-	- rm llama_cpp/*.lib
+	- rm falcon_cpp/*.so
+	- rm falcon_cpp/*.dylib
+	- rm falcon_cpp/*.metal
+	- rm falcon_cpp/*.dll
+	- rm falcon_cpp/*.lib
 
 .PHONY: \
 	update \
diff --git a/falcon_cpp/server/app.py b/falcon_cpp/server/app.py
@@ -24,7 +24,7 @@ class Settings(BaseSettings):
         default=None,
         description="The alias of the model to use for generating completions.",
     )
-    n_ctx: int = Field(default=2048, ge=1, description="The context size.")
+    n_ctx: int = Field(default=8192, ge=1, description="The context size.")
     n_gpu_layers: int = Field(
         default=0,
         ge=0,

Original file line number	Diff line number	Diff line change
`@@ -24,7 +24,7 @@ class Settings(BaseSettings):`
`24`	`24`	`default=None,`
`25`	`25`	`description="The alias of the model to use for generating completions.",`
`26`	`26`	`)`
`27`		`- n_ctx: int = Field(default=2048, ge=1, description="The context size.")`
	`27`	`+ n_ctx: int = Field(default=8192, ge=1, description="The context size.")`
`28`	`28`	`n_gpu_layers: int = Field(`
`29`	`29`	`default=0,`
`30`	`30`	`ge=0,`