starcoder - not working

[mirek190]

NOn the Roadmap May 2023 is see

I tried to run starcoder
https://huggingface.co/nouamanetazi/starcoder-ggml/tree/main

But getting error

main: build = 545 (bda4d7c)
main: seed = 1684021875
llama.cpp: loading model from models/starcoder-13b-q4_1.bin
error loading model: missing tok_embeddings.weight
llama_init_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model 'models/starcoder-13b-q4_1.bin'
main: error: unable to load model

Is that means is not implemented into llama.cpp yet ?

[BetaDoggo]

The mention on the roadmap was related to support in the ggml library itself, llama.cpp still only supports llama models.