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

feat(llama.cpp): support lora with scale and yarn (#1277)

Browse source 
* feat(llama.cpp): support lora with scale

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(llama.cpp): support yarn

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2023-11-11 18:40:48 +01:00 • committed by GitHub
parent bde87d00b9
commit 803a0ac02a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
13 changed files with 476 additions and 364 deletions
Download patch file Download diff file Expand all files Collapse all files

53
api/backend/options.go
View file

@ -38,30 +38,35 @@ func gRPCModelOpts(c config.Config) *pb.ModelOptions {
}
return &pb.ModelOptions{
ContextSize: int32(c.ContextSize),
Seed: int32(c.Seed),
NBatch: int32(b),
NoMulMatQ: c.NoMulMatQ,
DraftModel: c.DraftModel,
AudioPath: c.VallE.AudioPath,
Quantization: c.Quantization,
MMProj: c.MMProj,
LoraAdapter: c.LoraAdapter,
LoraBase: c.LoraBase,
NGQA: c.NGQA,
RMSNormEps: c.RMSNormEps,
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,
ContextSize: int32(c.ContextSize),
Seed: int32(c.Seed),
NBatch: int32(b),
NoMulMatQ: c.NoMulMatQ,
DraftModel: c.DraftModel,
AudioPath: c.VallE.AudioPath,
Quantization: c.Quantization,
MMProj: c.MMProj,
YarnExtFactor: c.YarnExtFactor,
YarnAttnFactor: c.YarnAttnFactor,
YarnBetaFast: c.YarnBetaFast,
YarnBetaSlow: c.YarnBetaSlow,
LoraAdapter: c.LoraAdapter,
LoraBase: c.LoraBase,
LoraScale: c.LoraScale,
NGQA: c.NGQA,
RMSNormEps: c.RMSNormEps,
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,
// AutoGPTQ
ModelBaseName: c.AutoGPTQ.ModelBaseName,
Device: c.AutoGPTQ.Device,