dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

fix: add rope settings during model load, fix CUDA (#821)

Browse source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2023-07-27 21:56:05 +02:00 • committed by GitHub
parent 147cae9ed8
commit 096d98c3d9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 176 additions and 148 deletions
Download patch file Download diff file Expand all files Collapse all files

28
api/backend/options.go
View file

@ -15,19 +15,21 @@ func gRPCModelOpts(c config.Config) *pb.ModelOptions {
b = c.Batch
}
return &pb.ModelOptions{
ContextSize: int32(c.ContextSize),
Seed: int32(c.Seed),
NBatch: int32(b),
F16Memory: c.F16,
MLock: c.MMlock,
NUMA: c.NUMA,
Embeddings: c.Embeddings,
LowVRAM: c.LowVRAM,
NGPULayers: int32(c.NGPULayers),
MMap: c.MMap,
MainGPU: c.MainGPU,
Threads: int32(c.Threads),
TensorSplit: c.TensorSplit,
ContextSize: int32(c.ContextSize),
Seed: int32(c.Seed),
NBatch: int32(b),
F16Memory: c.F16,
MLock: c.MMlock,
RopeFreqBase: c.RopeFreqBase,
RopeFreqScale: c.RopeFreqScale,
NUMA: c.NUMA,
Embeddings: c.Embeddings,
LowVRAM: c.LowVRAM,
NGPULayers: int32(c.NGPULayers),
MMap: c.MMap,
MainGPU: c.MainGPU,
Threads: int32(c.Threads),
TensorSplit: c.TensorSplit,
}
}