Description
I try using OpenAI-like API with vicuna LLM: python3 -m llama_cpp.server --n_gpu_layers 43 --model ./models/vicuna-13b-v1.5.Q8_0.gguf --port 8010 --host 0.0.0.0 --chat_format vicuna
Send request to endpoint /v1/chat/completions:
{
"max_tokens": 1024,
"temperature": 0.1,
"messages": [
{
"content": "Hello, what is your name?",
"role": "user"
},
{
"content": "My name is AI-asisstant",
"role": "assistant"
},
{
"content": "Can you repeat your name please?",
"role": "user"
}
]
}
And checking final prompt and final tokens. So, i see this:
PROMPT: A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hello, what is your name? ASSISTANT: My name is AI-asisstant </s>
USER: Can you repeat your name please? ASSISTANT:
PROMPT TOKENS: [1, 319, 13563, 1546, 263, 12758, 1404, 322, 385, 23116, 21082, 20255, 29889, 450, 20255, 4076, 8444, 29892, 13173, 29892, 322, 1248, 568, 6089, 304, 278, 1404, 29915, 29879, 5155, 29889, 3148, 1001, 29901, 15043, 29892, 825, 338, 596, 1024, 29973, 319, 1799, 9047, 13566, 29901, 1619, 1024, 338, 319, 29902, 29899, 25101, 303, 424, 829, 29879, 29958, 11889, 29901, 1815, 366, 12312, 596, 1024, 3113, 29973, 319, 1799, 9047, 13566, 29901]
I see that special token </s>
didn't correctly converted to token id (should be token id = 2) but converted to [29879, 29958]. It is bug?
I saw similar issue in discussion llama.cpp github repo - ggml-org/llama.cpp#1812
Activity
antoine-lizee commentedon Oct 30, 2023
@abetlen I second the above.
I'm not sure where to share this given that it impacts a few different things. In particular, proper handling of special characters, especially
</s>
is key for any conversation application. Indeed, a few models (and the top ones: Llama2, Mistral, etc...) rely on reserved tokens all along the conversation - those are not "just" strings.llama.cpp
solved the problem only recently (in ggml-org/llama.cpp#3538), and it now works.I think porting the change to llama-cpp-python will solve a few other problems that are shared around, eg: Chat Formats don't seem to work for instance ( #711 ).
Note: it might already be on your radar! Sorry if this is stating the obvious.
ggml : update cblas_sgemm columns var to be more reasonable (abetlen#838
antoine-lizee commentedon Oct 30, 2023
Ok, after checking out the latest version of the repo, we do have the right bindings (per this commit) but we don't have the correct default behaviour. As a result, llama-cpp-python behaves differently (and doesn't treat the special characters as it should).
I've opened PR #850 to propose a fix.