From 7fbe6006c9083b9a3b5a1e7b663f60f8df0200ab Mon Sep 17 00:00:00 2001 From: ochafik Date: Fri, 7 Jun 2024 09:42:21 +0100 Subject: [PATCH] update straggling refs --- .github/workflows/build.yml | 2 +- README-sycl.md | 2 +- examples/server/tests/README.md | 6 ++---- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 716a463cc..98e5244cb 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -240,7 +240,7 @@ jobs: echo "Fetch llama2c model" wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin ./bin/convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf - ./bin/main -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 + ./bin/llama -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256 - name: Determine tag name id: tag diff --git a/README-sycl.md b/README-sycl.md index 3dbe060e1..c7d45f3ad 100644 --- a/README-sycl.md +++ b/README-sycl.md @@ -77,7 +77,7 @@ It has the similar design of other llama.cpp BLAS-based paths such as *OpenBLAS, *Notes:* - **Memory** - - The device memory is a limitation when running a large model. The loaded model size, *`llm_load_tensors: buffer_size`*, is displayed in the log when running `./bin/main`. + - The device memory is a limitation when running a large model. The loaded model size, *`llm_load_tensors: buffer_size`*, is displayed in the log when running `./bin/llama`. - Please make sure the GPU shared memory from the host is large enough to account for the model's size. For e.g. the *llama-2-7b.Q4_0* requires at least 8.0GB for integrated GPU and 4.0GB for discrete GPU. diff --git a/examples/server/tests/README.md b/examples/server/tests/README.md index 1581c3862..5e6cb277b 100644 --- a/examples/server/tests/README.md +++ b/examples/server/tests/README.md @@ -27,10 +27,8 @@ To mitigate it, you can increase values in `n_predict`, `kv_size`. ```shell cd ../../.. -mkdir build -cd build -cmake -DLLAMA_CURL=ON ../ -cmake --build . --target llama-server +cmake -B build -DLLAMA_CURL=ON +cmake --build build --target llama-server ``` 2. Start the test: `./tests.sh`