Spaces:

ggml-org

/

gguf-my-repo

like 943

Running on A10G

I fine tuned Phi-3-128K instruct model using PEFT Lora and hosted the model to hugging face. It works fine but I am unable to convert it into GGUF format. While I am successfully converted the full fine tuned model. It says that "No such file or directory: 'CodePhi-3-mini-0.1Klora/config.json'\n'" while it a peft lora fine tuned model and I have hosted my fine tuned model on hugging face. The repository contains following files :
1: adapter_config.json
2: adapter_model.safetensors
3: special_tokens_map.json
4:tokenizer.json
5:tokenizer.model
6:tokenizer_config.json
7:training_args.bin
8: README.md
When I use "GGUF my repo" space to convert my peft lora fine tuned model i get the following error.

Error: Error converting to fp16: b'INFO:hf-to-gguf:Loading model: CodePhi-3-mini-0.1Klora\nTraceback (most recent call last):\n File "/home/user/app/llama.cpp/convert_hf_to_gguf.py", line 4149, in \n main()\n File "/home/user/app/llama.cpp/convert_hf_to_gguf.py", line 4117, in main\n hparams = Model.load_hparams(dir_model)\n File "/home/user/app/llama.cpp/convert_hf_to_gguf.py", line 423, in load_hparams\n with open(dir_model / "config.json", "r", encoding="utf-8") as f:\nFileNotFoundError: [Errno 2] No such file or directory: 'CodePhi-3-mini-0.1Klora/config.json'\n'