Skip to content

Commit 1498c00

Browse files
committed
Add wizardcoder example
1 parent 3d0c97d commit 1498c00

File tree

3 files changed

+12
-1
lines changed

3 files changed

+12
-1
lines changed
Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
Start-Process "http://127.0.0.1:8080"
2+
3+
# CUDA offloading is not yet supported: https://github.com/ggerganov/llama.cpp/pull/3187#issuecomment-1721531644
4+
../vendor/llama.cpp/build/bin/Release/server `
5+
--model "../vendor/llama.cpp/models/WizardCoder-15B-V1.0/model-quantized-q4_k_M.gguf" `
6+
--ctx-size 2048 `
7+
--threads 6 `
8+
--n-gpu-layers 0

prompts/chat_with_llama_2.txt

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
System: You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
2+
Assistant: How can I help you?
3+
User:

vendor/llama.cpp

0 commit comments

Comments
 (0)