Closed mofanke closed 2 months ago
Also request this model to be supported.
Tried to support it, use BertModel & SPM tokenizer. https://huggingface.co/vonjack/bge-m3-gguf
Tested cosine similarity between "中国" and "中华人民共和国": bge-m3-f16: 0.9993230772798457 mxbai-embed-large-v1-f16: 0.7287733321223814
I got error when using with langchain "terminate called after throwing an instance of 'std::out_of_range'"
same here with llama.cpp, the full error:
libc++abi: terminating due to uncaught exception of type std::out_of_range: unordered_map::at: key not found
the _bert version does not crash, but the the embeddings do not seem to have any sense...
also tried to follow instructions on https://github.com/PrithivirajDamodaran/blitz-embed but after converting to gguf, getting error:
llama_model_quantize: failed to quantize: key not found in model: bert.context_length
@vonjackustc can you share params you used with llama.cpp?
This issue was closed because it has been inactive for 14 days since being marked as stale.
@vonjackustc Same issue with @vuminhquang and @ciekawy when running it using Ollama.
It appears to be that embedding a text containing \n
(newline character) would result in the following error:
terminate called after throwing an instance of 'std::out_of_range'
what(): _Map_base::at
This issue is also brought up here: https://huggingface.co/vonjack/bge-m3-gguf/discussions/3.
BTW, as an alternative, I am using Text Embeddings Inference to run BAAI/bge-m3 now.
For embeddings I'd say most of the time it's safe if not desired to remove newlines. This may be not so obvious for longer texts but still...
Tried to support it, use BertModel & SPM tokenizer. https://huggingface.co/vonjack/bge-m3-gguf
Tested cosine similarity between "中国" and "中华人民共和国": bge-m3-f16: 0.9993230772798457 mxbai-embed-large-v1-f16: 0.7287733321223814
May I ask how exactly this is accomplished?
Prerequisites
Please answer the following questions for yourself before submitting an issue.
Feature Description
Supporting a multilingual embedding. https://huggingface.co/BAAI/bge-m3
Motivation
There are some differences between multilingual embeddings and BERT
Possible Implementation
sorry, no idea. I tried , seems model arch is same as bert ,but tokenizer is XLMRobertaTokenizer , not bertTokenizer