Merge branch 'master' into server-probs

Author: jhen0409

CMakeLists.txt

@@ -280,8 +280,8 @@ if (LLAMA_CUBLAS)
         # 52 == lowest CUDA 12 standard
         # 60 == f16 CUDA intrinsics
         # 61 == integer CUDA intrinsics
-        # 70 == (assumed) compute capability at which unrolling a loop in mul_mat_q kernels is faster
-        if (LLAMA_CUDA_DMMV_F16)
+        # 70 == compute capability at which unrolling a loop in mul_mat_q kernels is faster
+        if (LLAMA_CUDA_F16 OR LLAMA_CUDA_DMMV_F16)
             set(CMAKE_CUDA_ARCHITECTURES "60;61;70") # needed for f16 CUDA intrinsics
         else()
             set(CMAKE_CUDA_ARCHITECTURES "52;61;70") # lowest CUDA 12 standard + lowest for integer intrinsics

Makefile

@@ -340,6 +340,9 @@ llama.o: llama.cpp ggml.h ggml-alloc.h ggml-cuda.h ggml-metal.h llama.h llama-ut
 common.o: examples/common.cpp examples/common.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 
+console.o: examples/console.cpp examples/console.h
+	$(CXX) $(CXXFLAGS) -c $< -o $@
+
 grammar-parser.o: examples/grammar-parser.cpp examples/grammar-parser.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 
@@ -353,7 +356,7 @@ clean:
 # Examples
 #
 
-main: examples/main/main.cpp                                  build-info.h ggml.o llama.o common.o grammar-parser.o $(OBJS)
+main: examples/main/main.cpp                                  build-info.h ggml.o llama.o common.o console.o grammar-parser.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
 	@echo
 	@echo '====  Run ./main -h for help.  ===='
@@ -411,13 +414,13 @@ benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o
 vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
 
-tests/test-double-float: tests/test-double-float.c build-info.h ggml.o llama.o common.o $(OBJS)
+tests/test-double-float: tests/test-double-float.cpp build-info.h ggml.o llama.o common.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
 
-tests/test-grad0: tests/test-grad0.c build-info.h ggml.o llama.o common.o $(OBJS)
+tests/test-grad0: tests/test-grad0.cpp build-info.h ggml.o llama.o common.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
 
-tests/test-opt: tests/test-opt.c build-info.h ggml.o llama.o common.o $(OBJS)
+tests/test-opt: tests/test-opt.cpp build-info.h ggml.o llama.o common.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
 
 tests/test-quantize-fns: tests/test-quantize-fns.cpp build-info.h ggml.o llama.o common.o $(OBJS)

README.md

@@ -88,6 +88,7 @@ as the main playground for developing new features for the [ggml](https://github
 - [X] [Pygmalion 7B / Metharme 7B](#using-pygmalion-7b--metharme-7b)
 - [X] [WizardLM](https://github.com/nlpxucan/WizardLM)
 - [X] [Baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B) and its derivations (such as [baichuan-7b-sft](https://huggingface.co/hiyouga/baichuan-7b-sft))
+- [X] [Aquila-7B](https://huggingface.co/BAAI/Aquila-7B) / [AquilaChat-7B](https://huggingface.co/BAAI/AquilaChat-7B)
 
 **Bindings:**
 
@@ -492,13 +493,19 @@ Building the program with BLAS support may lead to some performance improvements
 # obtain the original LLaMA model weights and place them in ./models
 ls ./models
 65B 30B 13B 7B tokenizer_checklist.chk tokenizer.model
+  # [Optional] for models using BPE tokenizers
+  ls ./models
+  65B 30B 13B 7B vocab.json
 
 # install Python dependencies
 python3 -m pip install -r requirements.txt
 
 # convert the 7B model to ggml FP16 format
 python3 convert.py models/7B/
 
+  # [Optional] for models using BPE tokenizers
+  python convert.py models/7B/ --vocabtype bpe
+
 # quantize the model to 4-bits (using q4_0 method)
 ./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin q4_0
 

examples/CMakeLists.txt

@@ -13,6 +13,8 @@ set(TARGET common)
 add_library(${TARGET} OBJECT
     common.h
     common.cpp
+    console.h
+    console.cpp
     grammar-parser.h
     grammar-parser.cpp
     )