bartowski

/

stable-code-instruct-3b-GGUF

like 17

I have the most recent llama.cpp.

python convert.py ../models/stable-code-instruct-3b/ --outtype f32 --ctx 8192 --outfile ../models/stable-code-instruct-3b.fp32.bin 
Loading model file model-00001-of-00002.safetensors
Loading model file model-00001-of-00002.safetensors
Loading model file model-00002-of-00002.safetensors
Traceback (most recent call last):
  File "convert.py", line 1486, in <module>
    main()
  File "convert.py", line 1433, in main
    params = Params.load(model_plus)
             ^^^^^^^^^^^^^^^^^^^^^^^
  File "convert.py", line 317, in load
    params = Params.loadHFTransformerJson(model_plus.model, hf_config_path)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "convert.py", line 256, in loadHFTransformerJson
    f_norm_eps        = config["rms_norm_eps"],
                        ~~~~~~^^^^^^^^^^^^^^^^
KeyError: 'rms_norm_eps'

I'm not sure what is rms_norm_eps. any guidance appreciated.