feat: 增加模型；解决bug

fa8ce810 · chenpangpang · 9a3eef98 · 9a3eef98 · 9a3eef98 · 9a3eef98
Commit fa8ce810 authored Aug 09, 2024 by chenpangpang
20 changed files
--- a/llama.cpp/convert_llama_ggml_to_gguf.py
+++ b/llama.cpp/convert_llama_ggml_to_gguf.py
--- a/llama.cpp/convert_lora_to_gguf.py
+++ b/llama.cpp/convert_lora_to_gguf.py
--- a/llama.cpp/docs/android.md
+++ b/llama.cpp/docs/android.md
--- a/llama.cpp/docs/backend/BLIS.md
+++ b/llama.cpp/docs/backend/BLIS.md
--- a/llama.cpp/docs/backend/SYCL.md
+++ b/llama.cpp/docs/backend/SYCL.md
--- a/llama.cpp/docs/build.md
+++ b/llama.cpp/docs/build.md
--- a/llama.cpp/docs/development/HOWTO-add-model.md
+++ b/llama.cpp/docs/development/HOWTO-add-model.md
--- a/llama.cpp/docs/development/debugging-tests.md
+++ b/llama.cpp/docs/development/debugging-tests.md
--- a/llama.cpp/docs/development/llama-star/idea-arch.key
+++ b/llama.cpp/docs/development/llama-star/idea-arch.key
--- a/llama.cpp/docs/development/llama-star/idea-arch.pdf
+++ b/llama.cpp/docs/development/llama-star/idea-arch.pdf
--- a/llama.cpp/docs/development/token_generation_performance_tips.md
+++ b/llama.cpp/docs/development/token_generation_performance_tips.md
--- a/llama.cpp/docs/docker.md
+++ b/llama.cpp/docs/docker.md
--- a/llama.cpp/docs/install.md
+++ b/llama.cpp/docs/install.md
--- a/llama.cpp/examples/CMakeLists.txt
+++ b/llama.cpp/examples/CMakeLists.txt
--- a/llama.cpp/examples/Miku.sh
+++ b/llama.cpp/examples/Miku.sh
--- a/llama.cpp/examples/baby-llama/CMakeLists.txt
+++ b/llama.cpp/examples/baby-llama/CMakeLists.txt
--- a/llama.cpp/examples/baby-llama/baby-llama.cpp
+++ b/llama.cpp/examples/baby-llama/baby-llama.cpp
--- a/llama.cpp/examples/base-translate.sh
+++ b/llama.cpp/examples/base-translate.sh
--- a/llama.cpp/examples/batched-bench/CMakeLists.txt
+++ b/llama.cpp/examples/batched-bench/CMakeLists.txt
--- a/llama.cpp/examples/batched-bench/README.md
+++ b/llama.cpp/examples/batched-bench/README.md