mradermacher

/

model_requests

like 91

Selected as a best among code “embedders” at this board https://huggingface.co/spaces/mteb/leaderboard

We already tired this on 4th of May and back then it unfortunately failed with the following error due to using a pre-tokenizer not supported by llama.cpp. If you know what supported pre-tokenizer should be used instead, we could quant it using that one but we only so once someone confirmed it is safe to use a different pre-tokenizer as doing so could affect the model.

**************************************************************************************
** WARNING: The BPE pre-tokenizer was not recognized!
**          There are 2 possible reasons for this:
**          - the model has not been added to convert_hf_to_gguf_update.py yet
**          - the pre-tokenization config has changed upstream
**          Check your model files and convert_hf_to_gguf_update.py and update them accordingly.
** ref:     https://github.com/ggml-org/llama.cpp/pull/6920
**
** chkhsh:  d4540891389ea895b53b399da6ac824becc30f2fba0e9ddbb98f92e55ca0e97c
**************************************************************************************