llama-cpp-python 0.2.72__tar.gz → 0.2.74__tar.gz

llama_cpp_python-0.2.74/.git/FETCH_HEAD

@@ -0,0 +1 @@
+3c19faa0d4dc249e5dfdd9e3b79fe7d911ea0bfc		'3c19faa0d4dc249e5dfdd9e3b79fe7d911ea0bfc' of https://github.com/abetlen/llama-cpp-python

llama_cpp_python-0.2.74/.git/HEAD

@@ -0,0 +1 @@
+3c19faa0d4dc249e5dfdd9e3b79fe7d911ea0bfc

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/.git/config

@@ -9,7 +9,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX2tYQWhwWTVaa1FyalpaNEpWck9VNkV0VVl0UDZGWTJFNmNsYg==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzBFa2liaXp6ZEVPVG1nN2tscXg3bXFlQ3Y3a0hueTJ5QTBtVA==
 [submodule "vendor/llama.cpp"]
 	active = true
 	url = https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.74/.git/logs/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 3c19faa0d4dc249e5dfdd9e3b79fe7d911ea0bfc runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524424 +0000	checkout: moving from master to refs/tags/v0.2.74

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/HEAD

@@ -0,0 +1 @@
+b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/.git/modules/vendor/llama.cpp/config

@@ -16,7 +16,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX2tYQWhwWTVaa1FyalpaNEpWck9VNkV0VVl0UDZGWTJFNmNsYg==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzBFa2liaXp6ZEVPVG1nN2tscXg3bXFlQ3Y3a0hueTJ5QTBtVA==
 [url "https://github.com/"]
 	insteadOf = git@github.com:
 	insteadOf = org-6826477@github.com:

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2 runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524425 +0000	clone: from https://github.com/ggerganov/llama.cpp.git
+b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2 b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2 runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524425 +0000	checkout: moving from master to b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2 runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524425 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2 runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524425 +0000	clone: from https://github.com/ggerganov/llama.cpp.git

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/.git/modules/vendor/llama.cpp/modules/kompute/config

@@ -13,7 +13,7 @@
 [gc]
 	auto = 0
 [http "https://github.com/"]
-	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzX2tYQWhwWTVaa1FyalpaNEpWck9VNkV0VVl0UDZGWTJFNmNsYg==
+	extraheader = AUTHORIZATION: basic eC1hY2Nlc3MtdG9rZW46Z2hzXzBFa2liaXp6ZEVPVG1nN2tscXg3bXFlQ3Y3a0hueTJ5QTBtVA==
 [url "https://github.com/"]
 	insteadOf = git@github.com:
 	insteadOf = org-6826477@github.com:

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/modules/kompute/logs/HEAD

@@ -0,0 +1,2 @@
+0000000000000000000000000000000000000000 c339310f6ff914c5b94fb2353f01a33dfc35f64f runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524426 +0000	clone: from https://github.com/nomic-ai/kompute.git
+c339310f6ff914c5b94fb2353f01a33dfc35f64f 4565194ed7c32d1d2efa32ceab4d3c6cae006306 runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524426 +0000	checkout: moving from master to 4565194ed7c32d1d2efa32ceab4d3c6cae006306

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/heads/master

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 c339310f6ff914c5b94fb2353f01a33dfc35f64f runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524426 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/modules/kompute/logs/refs/remotes/origin/HEAD

@@ -0,0 +1 @@
+0000000000000000000000000000000000000000 c339310f6ff914c5b94fb2353f01a33dfc35f64f runner <runner@fv-az1442-408.gtdgxysclnuenlnkab13ghtgjb.cx.internal.cloudapp.net> 1715524426 +0000	clone: from https://github.com/nomic-ai/kompute.git

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/packed-refs

@@ -0,0 +1,2 @@
+# pack-refs with: peeled fully-peeled sorted 
+b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2 refs/remotes/origin/master

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/refs/heads/master

@@ -0,0 +1 @@
+b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/refs/tags/b2860

@@ -0,0 +1 @@
+b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2

llama_cpp_python-0.2.74/.git/modules/vendor/llama.cpp/shallow

@@ -0,0 +1 @@
+b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2

llama_cpp_python-0.2.74/.git/refs/tags/v0.2.74

@@ -0,0 +1 @@
+3c19faa0d4dc249e5dfdd9e3b79fe7d911ea0bfc

llama_cpp_python-0.2.74/.git/shallow

@@ -0,0 +1 @@
+3c19faa0d4dc249e5dfdd9e3b79fe7d911ea0bfc

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/CHANGELOG.md

@@ -7,6 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.74]
+
+- feat: Update llama.cpp to ggerganov/llama.cpp@b228aba91ac2cd9eb90e9d423ba1d0d20e0117e2
+- fix: Enable CUDA backend for llava by @abetlen in 7f59856fa6f3e23f07e12fc15aeb9359dc6c3bb4
+- docs: Fix typo in README.md by @yupbank in #1444
+
+## [0.2.73]
+
+- feat: Update llama.cpp to ggerganov/llama.cpp@25c6e82e7a1ad25a42b0894e87d9b5c557409516
+- fix: Clear kv cache at beginning of image chat formats to avoid bug when image is evaluated first by @abetlen in ac55d0a175115d1e719672ce1cb1bec776c738b1
+
 ## [0.2.72]
 
 - fix(security): Remote Code Execution by Server-Side Template Injection in Model Metadata by @retr0reg in b454f40a9a1787b2b5659cd2cb00819d983185df

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/CMakeLists.txt

@@ -51,8 +51,9 @@ if (LLAMA_BUILD)
     )
 
     if (LLAVA_BUILD)
-        if (LLAMA_CUBLAS)
+        if (LLAMA_CUBLAS OR LLAMA_CUDA)
             add_compile_definitions(GGML_USE_CUBLAS)
+            add_compile_definitions(GGML_USE_CUDA)
         endif()
 
         if (LLAMA_METAL)

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/Makefile

@@ -16,7 +16,7 @@ build.debug:
 	CMAKE_ARGS="-DCMAKE_BUILD_TYPE=Debug" python3 -m pip install --verbose --config-settings=cmake.verbose=true --config-settings=logging.level=INFO --config-settings=install.strip=false  --editable .
 
 build.cuda:
-	CMAKE_ARGS="-DLLAMA_CUBLAS=on" python3 -m pip install --verbose -e .
+	CMAKE_ARGS="-DLLAMA_CUDA=on" python3 -m pip install --verbose -e .
 
 build.opencl:
 	CMAKE_ARGS="-DLLAMA_CLBLAST=on" python3 -m pip install --verbose -e .

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama_cpp_python
-Version: 0.2.72
+Version: 0.2.74
 Summary: Python bindings for the llama.cpp library
 Author-Email: Andrei Betlen <abetlen@gmail.com>
 License: MIT
@@ -594,7 +594,7 @@ llm = Llama.from_pretrained(
   n_ctx=2048, # n_ctx should be increased to accommodate the image embedding
 )
 
-respoonse = llm.create_chat_completion(
+response = llm.create_chat_completion(
     messages = [
         {
             "role": "user",

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/README.md

@@ -550,7 +550,7 @@ llm = Llama.from_pretrained(
   n_ctx=2048, # n_ctx should be increased to accommodate the image embedding
 )
 
-respoonse = llm.create_chat_completion(
+response = llm.create_chat_completion(
     messages = [
         {
             "role": "user",

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/llama_cpp/__init__.py

@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.2.72"
+__version__ = "0.2.74"

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/llama_cpp/llama_chat_format.py

@@ -2637,6 +2637,7 @@ class Llava15ChatHandler:
 
         # Evaluate prompt
         llama.reset()
+        llama._ctx.kv_cache_clear()
         for type_, value in split_text:
             if type_ == "text":
                 tokens = llama.tokenize(value.encode("utf8"), add_bos=False, special=True)

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/CMakeLists.txt

@@ -405,6 +405,7 @@ if (LLAMA_CUDA)
         list(APPEND GGML_SOURCES_CUDA "ggml-cuda.cu")
 
         add_compile_definitions(GGML_USE_CUDA)
+        add_compile_definitions(GGML_CUDA_USE_GRAPHS)
         if (LLAMA_CUDA_FORCE_DMMV)
             add_compile_definitions(GGML_CUDA_FORCE_DMMV)
         endif()
@@ -430,7 +431,7 @@ if (LLAMA_CUDA)
 
         if (LLAMA_STATIC)
             if (WIN32)
-                # As of 12.3.1 CUDA Tookit for Windows does not offer a static cublas library
+                # As of 12.3.1 CUDA Toolkit for Windows does not offer a static cublas library
                 set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas CUDA::cublasLt)
             else ()
                 set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
@@ -1280,17 +1281,6 @@ install(
         WORLD_READ
         WORLD_EXECUTE
     DESTINATION ${CMAKE_INSTALL_BINDIR})
-install(
-    FILES convert-lora-to-ggml.py
-    PERMISSIONS
-        OWNER_READ
-        OWNER_WRITE
-        OWNER_EXECUTE
-        GROUP_READ
-        GROUP_EXECUTE
-        WORLD_READ
-        WORLD_EXECUTE
-    DESTINATION ${CMAKE_INSTALL_BINDIR})
 if (LLAMA_METAL)
     install(
         FILES ggml-metal.metal

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/Makefile

@@ -433,7 +433,7 @@ ifdef LLAMA_CUDA
 	else
 		CUDA_PATH ?= /usr/local/cuda
 	endif
-	MK_CPPFLAGS  += -DGGML_USE_CUDA -I$(CUDA_PATH)/include -I$(CUDA_PATH)/targets/$(UNAME_M)-linux/include
+	MK_CPPFLAGS  += -DGGML_USE_CUDA -I$(CUDA_PATH)/include -I$(CUDA_PATH)/targets/$(UNAME_M)-linux/include -DGGML_CUDA_USE_GRAPHS
 	MK_LDFLAGS   += -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L$(CUDA_PATH)/lib64 -L/usr/lib64 -L$(CUDA_PATH)/targets/$(UNAME_M)-linux/lib -L/usr/lib/wsl/lib
 	OBJS         += ggml-cuda.o
 	OBJS         += $(patsubst %.cu,%.o,$(wildcard ggml-cuda/*.cu))

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/README.md

@@ -2,7 +2,7 @@
 
 ![llama](https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png)
 
-[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![Server](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml/badge.svg?branch=master&event=schedule)](https://github.com/ggerganov/llama.cpp/actions/workflows/server.yml)
 
 [Roadmap](https://github.com/users/ggerganov/projects/7) / [Project status](https://github.com/ggerganov/llama.cpp/discussions/3471) / [Manifesto](https://github.com/ggerganov/llama.cpp/discussions/205) / [ggml](https://github.com/ggerganov/ggml)
 
@@ -176,6 +176,7 @@ Unless otherwise noted these projects are open-source with permissive licensing:
 - [nat/openplayground](https://github.com/nat/openplayground)
 - [Faraday](https://faraday.dev/) (proprietary)
 - [LMStudio](https://lmstudio.ai/) (proprietary)
+- [Layla](https://play.google.com/store/apps/details?id=com.laylalite) (proprietary)
 - [LocalAI](https://github.com/mudler/LocalAI) (MIT)
 - [LostRuins/koboldcpp](https://github.com/LostRuins/koboldcpp) (AGPL)
 - [Mozilla-Ocho/llamafile](https://github.com/Mozilla-Ocho/llamafile)

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/ci/run.sh

@@ -365,47 +365,6 @@ function gg_run_open_llama_3b_v2 {
 
     cat $OUT/${ci}-imatrix.log | grep "Final" >> $OUT/${ci}-imatrix-sum.log
 
-    # lora
-    function compare_ppl {
-        qnt="$1"
-        ppl1=$(echo "$2" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1)
-        ppl2=$(echo "$3" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1)
-
-        if [ $(echo "$ppl1 < $ppl2" | bc) -eq 1 ]; then
-            printf '  - %s @ %s (FAIL: %s > %s)\n' "$qnt" "$ppl" "$ppl1" "$ppl2"
-            return 20
-        fi
-
-        printf '  - %s @ %s %s OK\n' "$qnt" "$ppl1" "$ppl2"
-        return 0
-    }
-
-    path_lora="../models-mnt/open-llama/3B-v2/lora"
-    path_shakespeare="../models-mnt/shakespeare"
-
-    shakespeare="${path_shakespeare}/shakespeare.txt"
-    lora_shakespeare="${path_lora}/ggml-adapter-model.bin"
-
-    gg_wget ${path_lora} https://huggingface.co/slaren/open_llama_3b_v2_shakespeare_lora/resolve/main/adapter_config.json
-    gg_wget ${path_lora} https://huggingface.co/slaren/open_llama_3b_v2_shakespeare_lora/resolve/main/adapter_model.bin
-    gg_wget ${path_shakespeare} https://huggingface.co/slaren/open_llama_3b_v2_shakespeare_lora/resolve/main/shakespeare.txt
-
-    python3 ../convert-lora-to-ggml.py ${path_lora}
-
-    # f16
-    (time ./bin/perplexity --model ${model_f16} -f ${shakespeare}                            -c 128 -b 128 --chunks 1 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-f16.log
-    (time ./bin/perplexity --model ${model_f16} -f ${shakespeare} --lora ${lora_shakespeare} -c 128 -b 128 --chunks 1 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-lora-f16.log
-    compare_ppl "f16 shakespeare" "$(cat $OUT/${ci}-ppl-shakespeare-f16.log | grep "^\[1\]")" "$(cat $OUT/${ci}-ppl-shakespeare-lora-f16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-lora-ppl.log
-
-    # q8_0
-    (time ./bin/perplexity --model ${model_q8_0} -f ${shakespeare}                            -c 128 -b 128 --chunks 1 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-q8_0.log
-    (time ./bin/perplexity --model ${model_q8_0} -f ${shakespeare} --lora ${lora_shakespeare} -c 128 -b 128 --chunks 1 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-lora-q8_0.log
-    compare_ppl "q8_0 shakespeare" "$(cat $OUT/${ci}-ppl-shakespeare-q8_0.log | grep "^\[1\]")" "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0.log | grep "^\[1\]")" | tee -a $OUT/${ci}-lora-ppl.log
-
-    # q8_0 + f16 lora-base
-    (time ./bin/perplexity --model ${model_q8_0} -f ${shakespeare} --lora ${lora_shakespeare} --lora-base ${model_f16} -c 128 -b 128 --chunks 1 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-lora-q8_0-f16.log
-    compare_ppl "q8_0 / f16 base shakespeare" "$(cat $OUT/${ci}-ppl-shakespeare-q8_0.log | grep "^\[1\]")" "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0-f16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-lora-ppl.log
-
     set +e
 }
 
@@ -416,7 +375,6 @@ function gg_sum_open_llama_3b_v2 {
     gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)"
     gg_printf '- perplexity:\n%s\n' "$(cat $OUT/${ci}-ppl.log)"
     gg_printf '- imatrix:\n```\n%s\n```\n' "$(cat $OUT/${ci}-imatrix-sum.log)"
-    gg_printf '- lora:\n%s\n' "$(cat $OUT/${ci}-lora-ppl.log)"
     gg_printf '- f16: \n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-f16.log)"
     gg_printf '- q8_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q8_0.log)"
     gg_printf '- q4_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q4_0.log)"
@@ -429,11 +387,6 @@ function gg_sum_open_llama_3b_v2 {
     gg_printf '- q5_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q5_k.log)"
     gg_printf '- q6_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q6_k.log)"
     gg_printf '- save-load-state: \n```\n%s\n```\n' "$(cat $OUT/${ci}-save-load-state.log)"
-    gg_printf '- shakespeare (f16):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-f16.log)"
-    gg_printf '- shakespeare (f16 lora):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-lora-f16.log)"
-    gg_printf '- shakespeare (q8_0):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-q8_0.log)"
-    gg_printf '- shakespeare (q8_0 lora):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0.log)"
-    gg_printf '- shakespeare (q8_0 / f16 base lora):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0-f16.log)"
 }
 
 # open_llama_7b_v2
@@ -549,48 +502,6 @@ function gg_run_open_llama_7b_v2 {
 
     cat $OUT/${ci}-imatrix.log | grep "Final" >> $OUT/${ci}-imatrix-sum.log
 
-    # lora
-    function compare_ppl {
-        qnt="$1"
-        ppl1=$(echo "$2" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1)
-        ppl2=$(echo "$3" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1)
-
-        if [ $(echo "$ppl1 < $ppl2" | bc) -eq 1 ]; then
-            printf '  - %s @ %s (FAIL: %s > %s)\n' "$qnt" "$ppl" "$ppl1" "$ppl2"
-            return 20
-        fi
-
-        printf '  - %s @ %s %s OK\n' "$qnt" "$ppl1" "$ppl2"
-        return 0
-    }
-
-    path_lora="../models-mnt/open-llama/7B-v2/lora"
-    path_shakespeare="../models-mnt/shakespeare"
-
-    shakespeare="${path_shakespeare}/shakespeare.txt"
-    lora_shakespeare="${path_lora}/ggml-adapter-model.bin"
-
-    gg_wget ${path_lora} https://huggingface.co/slaren/open_llama_7b_v2_shakespeare_lora/resolve/main/adapter_config.json
-    gg_wget ${path_lora} https://huggingface.co/slaren/open_llama_7b_v2_shakespeare_lora/resolve/main/adapter_model.bin
-    gg_wget ${path_shakespeare} https://huggingface.co/slaren/open_llama_7b_v2_shakespeare_lora/resolve/main/shakespeare.txt
-
-    python3 ../convert-lora-to-ggml.py ${path_lora}
-
-    # f16
-    (time ./bin/perplexity --model ${model_f16} -f ${shakespeare}                            -t 1 -ngl 999 -c 2048 -b 512 --chunks 3 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-f16.log
-    (time ./bin/perplexity --model ${model_f16} -f ${shakespeare} --lora ${lora_shakespeare} -t 1 -ngl 999 -c 2048 -b 512 --chunks 3 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-lora-f16.log
-    compare_ppl "f16 shakespeare" "$(cat $OUT/${ci}-ppl-shakespeare-f16.log | grep "^\[1\]")" "$(cat $OUT/${ci}-ppl-shakespeare-lora-f16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-lora-ppl.log
-
-    # currently not supported by the CUDA backend
-    # q8_0
-    #(time ./bin/perplexity --model ${model_q8_0} -f ${shakespeare}                            -t 1 -ngl 999 -c 2048 -b 512 --chunks 3 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-q8_0.log
-    #(time ./bin/perplexity --model ${model_q8_0} -f ${shakespeare} --lora ${lora_shakespeare} -t 1 -ngl 999 -c 2048 -b 512 --chunks 3 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-lora-q8_0.log
-    #compare_ppl "q8_0 shakespeare" "$(cat $OUT/${ci}-ppl-shakespeare-q8_0.log | grep "^\[1\]")" "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0.log | grep "^\[1\]")" | tee -a $OUT/${ci}-lora-ppl.log
-
-    # q8_0 + f16 lora-base
-    #(time ./bin/perplexity --model ${model_q8_0} -f ${shakespeare} --lora ${lora_shakespeare} --lora-base ${model_f16} -t 1 -ngl 999 -c 2048 -b 512 --chunks 3 ) 2>&1 | tee -a $OUT/${ci}-ppl-shakespeare-lora-q8_0-f16.log
-    #compare_ppl "q8_0 / f16 shakespeare" "$(cat $OUT/${ci}-ppl-shakespeare-q8_0.log | grep "^\[1\]")" "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0-f16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-lora-ppl.log
-
     set +e
 }
 
@@ -601,7 +512,6 @@ function gg_sum_open_llama_7b_v2 {
     gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)"
     gg_printf '- perplexity:\n%s\n' "$(cat $OUT/${ci}-ppl.log)"
     gg_printf '- imatrix:\n```\n%s\n```\n' "$(cat $OUT/${ci}-imatrix-sum.log)"
-    gg_printf '- lora:\n%s\n' "$(cat $OUT/${ci}-lora-ppl.log)"
     gg_printf '- f16: \n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-f16.log)"
     gg_printf '- q8_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q8_0.log)"
     gg_printf '- q4_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q4_0.log)"
@@ -614,11 +524,6 @@ function gg_sum_open_llama_7b_v2 {
     gg_printf '- q5_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q5_k.log)"
     gg_printf '- q6_k:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q6_k.log)"
     gg_printf '- save-load-state: \n```\n%s\n```\n' "$(cat $OUT/${ci}-save-load-state.log)"
-    gg_printf '- shakespeare (f16):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-f16.log)"
-    gg_printf '- shakespeare (f16 lora):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-lora-f16.log)"
-    #gg_printf '- shakespeare (q8_0):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-q8_0.log)"
-    #gg_printf '- shakespeare (q8_0 lora):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0.log)"
-    #gg_printf '- shakespeare (q8_0 / f16 base lora):\n```\n%s\n```\n' "$(cat $OUT/${ci}-ppl-shakespeare-lora-q8_0-f16.log)"
 }
 
 # bge-small

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/common/build-info.cpp

@@ -1,4 +1,4 @@
 int LLAMA_BUILD_NUMBER = 1;
-char const *LLAMA_COMMIT = "911b390";
+char const *LLAMA_COMMIT = "b228aba";
 char const *LLAMA_COMPILER = "cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0";
 char const *LLAMA_BUILD_TARGET = "x86_64-linux-gnu";

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/common/common.cpp

@@ -1,4 +1,6 @@
 #include "common.h"
+// Change JSON_ASSERT from assert() to GGML_ASSERT:
+#define JSON_ASSERT GGML_ASSERT
 #include "json.hpp"
 #include "json-schema-to-grammar.h"
 #include "llama.h"
@@ -899,6 +901,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
         params.interactive = true;
         return true;
     }
+    if (arg == "--interactive-specials") {
+        params.interactive_specials = true;
+        return true;
+    }
     if (arg == "--embedding") {
         params.embedding = true;
         return true;
@@ -911,6 +917,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
         params.instruct = true;
         return true;
     }
+    if (arg == "-cnv" || arg == "--conversation") {
+        params.conversation = true;
+        return true;
+    }
     if (arg == "-cml" || arg == "--chatml") {
         params.chatml = true;
         return true;
@@ -1361,14 +1371,12 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
         if (arg.compare(0, arg_prefix.size(), arg_prefix) == 0) {
             std::replace(arg.begin(), arg.end(), '_', '-');
         }
-
         if (!gpt_params_find_arg(argc, argv, arg, params, i, invalid_param)) {
             throw std::invalid_argument("error: unknown argument: " + arg);
         }
-    }
-
-    if (invalid_param) {
-        throw std::invalid_argument("error: invalid parameter for argument: " + arg);
+        if (invalid_param) {
+            throw std::invalid_argument("error: invalid parameter for argument: " + arg);
+        }
     }
 
     if (params.prompt_cache_all &&
@@ -1416,7 +1424,9 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("  -h, --help            show this help message and exit\n");
     printf("  --version             show version and build info\n");
     printf("  -i, --interactive     run in interactive mode\n");
+    printf("  --interactive-specials allow special tokens in user text, in interactive mode\n");
     printf("  --interactive-first   run in interactive mode and wait for input right away\n");
+    printf("  -cnv, --conversation  run in conversation mode (does not print special tokens and suffix/prefix)\n");
     printf("  -ins, --instruct      run in instruction mode (use with Alpaca models)\n");
     printf("  -cml, --chatml        run in chatml mode (use with ChatML-compatible models)\n");
     printf("  --multiline-input     allows you to write or paste multiple lines without ending each in '\\'\n");
@@ -1964,18 +1974,18 @@ static bool llama_download_file(const std::string & url, const std::string & pat
             try {
                 metadata_in >> metadata;
                 fprintf(stderr, "%s: previous metadata file found %s: %s\n", __func__, metadata_path.c_str(), metadata.dump().c_str());
-                if (metadata.contains("url") && metadata["url"].is_string()) {
-                    auto previous_url = metadata["url"].get<std::string>();
+                if (metadata.contains("url") && metadata.at("url").is_string()) {
+                    auto previous_url = metadata.at("url").get<std::string>();
                     if (previous_url != url) {
                         fprintf(stderr, "%s: Model URL mismatch: %s != %s\n", __func__, url.c_str(), previous_url.c_str());
                         return false;
                     }
                 }
-                if (metadata.contains("etag") && metadata["etag"].is_string()) {
-                    etag = metadata["etag"];
+                if (metadata.contains("etag") && metadata.at("etag").is_string()) {
+                    etag = metadata.at("etag");
                 }
-                if (metadata.contains("lastModified") && metadata["lastModified"].is_string()) {
-                    last_modified = metadata["lastModified"];
+                if (metadata.contains("lastModified") && metadata.at("lastModified").is_string()) {
+                    last_modified = metadata.at("lastModified");
                 }
             } catch (const nlohmann::json::exception & e) {
                 fprintf(stderr, "%s: error reading metadata file %s: %s\n", __func__, metadata_path.c_str(), e.what());
@@ -2645,6 +2655,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
     dump_string_yaml_multiline(stream, "in_suffix", params.input_prefix.c_str());
     fprintf(stream, "instruct: %s # default: false\n", params.instruct ? "true" : "false");
     fprintf(stream, "interactive: %s # default: false\n", params.interactive ? "true" : "false");
+    fprintf(stream, "interactive_specials: %s # default: false\n", params.interactive_specials ? "true" : "false");
     fprintf(stream, "interactive_first: %s # default: false\n", params.interactive_first ? "true" : "false");
     fprintf(stream, "keep: %d # default: 0\n", params.n_keep);
     fprintf(stream, "logdir: %s # default: unset (no logging)\n", params.logdir.c_str());

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/common/common.h

@@ -140,6 +140,8 @@ struct gpt_params {
     bool random_prompt     = false; // do not randomize prompt if none provided
     bool use_color         = false; // use color to distinguish generations and inputs
     bool interactive       = false; // interactive mode
+    bool interactive_specials = false; // whether to allow special tokens from user, during interactive mode
+    bool conversation      = false; // conversation mode (does not print special tokens and suffix/prefix)
     bool chatml            = false; // chatml mode (used for models trained on chatml syntax)
     bool prompt_cache_all  = false; // save user input and generations to prompt cache
     bool prompt_cache_ro   = false; // open the prompt cache read-only and do not update it

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/common/grammar-parser.cpp

@@ -142,6 +142,9 @@ namespace grammar_parser {
                 pos++;
                 last_sym_start = out_elements.size();
                 while (*pos != '"') {
+                    if (!*pos) {
+                        throw std::runtime_error("unexpected end of input");
+                    }
                     auto char_pair = parse_char(pos);
                          pos       = char_pair.second;
                     out_elements.push_back({LLAMA_GRETYPE_CHAR, char_pair.first});
@@ -156,6 +159,9 @@ namespace grammar_parser {
                 }
                 last_sym_start = out_elements.size();
                 while (*pos != ']') {
+                    if (!*pos) {
+                        throw std::runtime_error("unexpected end of input");
+                    }
                     auto char_pair = parse_char(pos);
                          pos       = char_pair.second;
                     enum llama_gretype type = last_sym_start < out_elements.size()
@@ -164,6 +170,9 @@ namespace grammar_parser {
 
                     out_elements.push_back({type, char_pair.first});
                     if (pos[0] == '-' && pos[1] != ']') {
+                        if (!pos[1]) {
+                            throw std::runtime_error("unexpected end of input");
+                        }
                         auto endchar_pair = parse_char(pos + 1);
                              pos          = endchar_pair.second;
                         out_elements.push_back({LLAMA_GRETYPE_CHAR_RNG_UPPER, endchar_pair.first});

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/common/json-schema-to-grammar.h

@@ -1,4 +1,8 @@
 #pragma once
+
+#include "ggml.h"
+// Change JSON_ASSERT from assert() to GGML_ASSERT:
+#define JSON_ASSERT GGML_ASSERT
 #include "json.hpp"
 
 std::string json_schema_to_grammar(const nlohmann::ordered_json& schema);

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/common/sampling.cpp

@@ -35,7 +35,7 @@ struct llama_sampling_context * llama_sampling_init(const struct llama_sampling_
 
     result->prev.resize(params.n_prev);
 
-    result->n_considered = 0;
+    result->n_valid = 0;
 
     llama_sampling_set_rng_seed(result, params.seed);
 
@@ -66,7 +66,7 @@ void llama_sampling_reset(llama_sampling_context * ctx) {
 
     std::fill(ctx->prev.begin(), ctx->prev.end(), 0);
     ctx->cur.clear();
-    ctx->n_considered = 0;
+    ctx->n_valid = 0;
 }
 
 void llama_sampling_set_rng_seed(struct llama_sampling_context * ctx, uint32_t seed) {
@@ -256,7 +256,7 @@ static llama_token llama_sampling_sample_impl(
         }
     }
 
-    ctx_sampling->n_considered = cur_p.size;
+    ctx_sampling->n_valid = temp == 0.0f ? 0 : cur_p.size;
 
     return id;
 }

{llama_cpp_python-0.2.72 → llama_cpp_python-0.2.74}/vendor/llama.cpp/common/sampling.h

@@ -81,7 +81,7 @@ struct llama_sampling_context {
     // TODO: replace with ring-buffer
     std::vector<llama_token>      prev;
     std::vector<llama_token_data> cur;
-    size_t n_considered;
+    size_t n_valid; // Number of correct top tokens with correct probabilities.
 
     std::mt19937 rng;
 };