vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : support input embeddings directly (#1910)

Browse source 
* add interface for float input

* fixed inpL shape and type

* add examples of input floats

* add test example for embd input

* fixed sampling

* add free for context

* fixed add end condition for generating

* add examples for llava.py

* add READMD for llava.py

* add READMD for llava.py

* add example of PandaGPT

* refactor the interface and fixed the styles

* add cmake build for embd-input

* add cmake build for embd-input

* Add MiniGPT-4 example

* change the order of the args of llama_eval_internal

* fix ci error
This commit is contained in:
ningshanwutuobang 2023-06-28 23:53:37 +08:00 • committed by GitHub
parent 9d23589d63
commit cfa0750bc9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
16 changed files with 811 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

11
Makefile
View file

@ -1,5 +1,5 @@
# Define the default target now so that it is always the first target
BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot train-text-from-scratch simple
BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot train-text-from-scratch simple libembdinput.so embd-input-test
ifdef LLAMA_BUILD_SERVER
BUILD_TARGETS += server
@ -272,7 +272,7 @@ libllama.so: llama.o ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
clean:
rm -vf *.o *.so main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server vdot train-text-from-scratch build-info.h
rm -vf *.o *.so main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server vdot train-text-from-scratch embd-input-test build-info.h
#
# Examples
@ -305,6 +305,13 @@ save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.
server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp build-info.h ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS)
libembdinput.so: examples/embd-input/embd-input.h examples/embd-input/embd-input-lib.cpp build-info.h ggml.o llama.o common.o $(OBJS)
$(CXX) --shared $(CXXFLAGS) $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS)
embd-input-test: libembdinput.so examples/embd-input/embd-input-test.cpp build-info.h ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.so,$(filter-out %.h,$(filter-out %.hpp,$^))) -o $@ $(LDFLAGS) -L. -lembdinput
train-text-from-scratch: examples/train-text-from-scratch/train-text-from-scratch.cpp build-info.h ggml.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)