Merge branch 'master' into HEAD
This commit is contained in:
Georgi Gerganov
commit
891ac40668
3 changed files with 37 additions and 20 deletions
49
Makefile
49
Makefile
|
|
@ -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 convert-llama2c-to-ggml simple server embd-input-test gguf llama-bench
|
||||
BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot train-text-from-scratch convert-llama2c-to-ggml simple save-load-state server embd-input-test gguf llama-bench baby-llama beam_search
|
||||
|
||||
# Binaries only useful for tests
|
||||
TEST_TARGETS = tests/test-llama-grammar tests/test-grammar-parser tests/test-double-float tests/test-grad0 tests/test-opt tests/test-quantize-fns tests/test-quantize-perf tests/test-sampling tests/test-tokenizer-0-llama tests/test-tokenizer-0-falcon tests/test-tokenizer-1
|
||||
|
|
@ -361,7 +361,7 @@ OBJS += ggml-alloc.o
|
|||
llama.o: llama.cpp ggml.h ggml-alloc.h ggml-cuda.h ggml-metal.h llama.h
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
common.o: common/common.cpp common/common.h common/log.h
|
||||
common.o: common/common.cpp common/common.h build-info.h common/log.h
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
console.o: common/console.cpp common/console.h
|
||||
|
|
@ -374,7 +374,7 @@ libllama.so: llama.o ggml.o $(OBJS)
|
|||
$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
|
||||
|
||||
clean:
|
||||
rm -vf *.o *.so *.dll main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server simple vdot train-text-from-scratch convert-llama2c-to-ggml embd-input-test gguf llama-bench build-info.h $(TEST_TARGETS)
|
||||
rm -vf *.o *.so *.dll benchmark-matmult build-info.h $(BUILD_TARGETS) $(TEST_TARGETS)
|
||||
|
||||
#
|
||||
# Examples
|
||||
|
|
@ -414,18 +414,33 @@ $(LIB_PRE)embdinput$(DSO_EXT): examples/embd-input/embd-input.h examples/embd-in
|
|||
embd-input-test: $(LIB_PRE)embdinput$(DSO_EXT) examples/embd-input/embd-input-test.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %$(DSO_EXT),$(filter-out %.h,$(filter-out %.hpp,$^))) -o $@ $(LDFLAGS) -L. -lembdinput
|
||||
|
||||
gguf: examples/gguf/gguf.cpp build-info.h ggml.o llama.o $(OBJS)
|
||||
gguf: examples/gguf/gguf.cpp ggml.o llama.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
train-text-from-scratch: examples/train-text-from-scratch/train-text-from-scratch.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
train-text-from-scratch: examples/train-text-from-scratch/train-text-from-scratch.cpp ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
convert-llama2c-to-ggml: examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp build-info.h ggml.o llama.o $(OBJS)
|
||||
convert-llama2c-to-ggml: examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp ggml.o llama.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
llama-bench: examples/llama-bench/llama-bench.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
baby-llama: examples/baby-llama/baby-llama.cpp ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
beam_search: examples/beam_search/beam_search.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
ifneq '' '$(or $(filter clean,$(MAKECMDGOALS)),$(LLAMA_METAL))'
|
||||
BUILD_TARGETS += metal
|
||||
endif
|
||||
|
||||
ifdef LLAMA_METAL
|
||||
metal: examples/metal/metal.cpp ggml.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
||||
endif
|
||||
|
||||
build-info.h: $(wildcard .git/index) scripts/build-info.sh
|
||||
@sh scripts/build-info.sh > $@.tmp
|
||||
@if ! cmp -s $@.tmp $@; then \
|
||||
|
|
@ -448,34 +463,34 @@ vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
|
|||
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-llama-grammar: tests/test-llama-grammar.cpp build-info.h ggml.o common.o grammar-parser.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-grammar-parser: tests/test-grammar-parser.cpp build-info.h ggml.o llama.o common.o grammar-parser.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
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)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-grad0: tests/test-grad0.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-opt: tests/test-opt.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-quantize-fns: tests/test-quantize-fns.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-quantize-perf: tests/test-quantize-perf.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-sampling: tests/test-sampling.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-tokenizer-0-falcon: tests/test-tokenizer-0-falcon.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-tokenizer-0-llama: tests/test-tokenizer-0-llama.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-tokenizer-1: tests/test-tokenizer-1.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
|
|
|
|||
|
|
@ -113,6 +113,7 @@ as the main playground for developing new features for the [ggml](https://github
|
|||
- C#/.NET: [SciSharp/LLamaSharp](https://github.com/SciSharp/LLamaSharp)
|
||||
- Scala 3: [donderom/llm4s](https://github.com/donderom/llm4s)
|
||||
- Clojure: [phronmophobic/llama.clj](https://github.com/phronmophobic/llama.clj)
|
||||
- React Native: [mybigday/llama.rn](https://github.com/mybigday/llama.rn)
|
||||
|
||||
**UI:**
|
||||
|
||||
|
|
|
|||
|
|
@ -469,7 +469,7 @@ class UnquantizedTensor(Tensor):
|
|||
|
||||
def permute_part(self, n_part: int, n_head: int) -> 'UnquantizedTensor':
|
||||
r = self.ndarray.shape[0] // 3
|
||||
return UnquantizedTensor(permute(self.ndarray[r * n_part : r * n_part + r, ...], n_head))
|
||||
return UnquantizedTensor(permute(self.ndarray[r * n_part : r * n_part + r, ...], n_head, n_head))
|
||||
|
||||
def part(self, n_part: int) -> 'UnquantizedTensor':
|
||||
r = self.ndarray.shape[0] // 3
|
||||
|
|
@ -952,9 +952,10 @@ def convert_model_names(model: LazyModel, params: Params) -> LazyModel:
|
|||
#tmp[f"model.layers.{i}.self_attn.v_proj.weight"] = model[f"model.layers.{i}.self_attn.v_proj.weight"]
|
||||
elif f"model.layers.{i}.self_attn.W_pack.weight" in model:
|
||||
print(f"Unpacking and permuting layer {i}")
|
||||
tmp[f"model.layers.{i}.self_attn.q_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 0, params.n_head, params.n_head)
|
||||
tmp[f"model.layers.{i}.self_attn.k_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 1, params.n_head, params.n_head_kv)
|
||||
tmp[f"model.layers.{i}.self_attn.q_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 0, params.n_head)
|
||||
tmp[f"model.layers.{i}.self_attn.k_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 1, params.n_head)
|
||||
tmp[f"model.layers.{i}.self_attn.v_proj.weight"] = part_lazy (model[f"model.layers.{i}.self_attn.W_pack.weight"], 2)
|
||||
del tmp[f"model.layers.{i}.self_attn.W_pack.weight"]
|
||||
else:
|
||||
break
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue