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

examples : add "retrieval" (#6193)

Browse source 
* add `retrieval` example

* add README

* minor fixes

* cast filepos on print

* remove use of variable sized array

* store similarities in separate vector

* print error on insufficient batch size

* fix error message printing

* assign n_batch value to n_ubatch

* fix param definitions

* define retrieval-only parameters in retrieval.cpp

* fix `--context-file` option to be provided multiple times for multiple files

* use vector for `query_emb`

* add usage description in README

* fix merge conflict

* fix usage printing

* remove seed setting

* fix lint

* increase file read buffer size

* retrieval : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Minsoo Cheong 2024-03-25 16:38:22 +09:00 • committed by GitHub
parent 7733f0c760
commit 64e7b47c69
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 435 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
Makefile
View file

@ -2,7 +2,7 @@
BUILD_TARGETS = \
main quantize quantize-stats perplexity imatrix embedding vdot q8dot train-text-from-scratch convert-llama2c-to-ggml \
simple batched batched-bench save-load-state server gguf gguf-split llama-bench libllava.a llava-cli baby-llama beam-search \
speculative infill tokenize benchmark-matmult parallel finetune export-lora lookahead lookup passkey gritlm tests/test-c.o
retrieval speculative infill tokenize benchmark-matmult parallel finetune export-lora lookahead lookup passkey gritlm tests/test-c.o
# Binaries only useful for tests
TEST_TARGETS = \
@ -804,6 +804,10 @@ export-lora: examples/export-lora/export-lora.cpp ggml.o common/common.h $(OBJS)
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
retrieval: examples/retrieval/retrieval.cpp ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
speculative: examples/speculative/speculative.cpp ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)