error loading model: invalid character
i am getting the following while trying to load with llama.cpp, any idea how to fix it? all other gguf models are working fine with the same main.exe. I have the latest build of llama.cpp
...
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: general.name str
llama_model_loader: - kv 2: starcoder.context_length u32
llama_model_loader: - kv 3: starcoder.embedding_length u32
llama_model_loader: - kv 4: starcoder.feed_forward_length u32
llama_model_loader: - kv 5: starcoder.block_count u32
llama_model_loader: - kv 6: starcoder.attention.head_count u32
llama_model_loader: - kv 7: starcoder.attention.head_count_kv u32
llama_model_loader: - kv 8: starcoder.attention.layer_norm_epsilon f32
llama_model_loader: - kv 9: general.file_type u32
llama_model_loader: - kv 10: tokenizer.ggml.model str
llama_model_loader: - kv 11: tokenizer.ggml.tokens arr
llama_model_loader: - kv 12: tokenizer.ggml.scores arr
llama_model_loader: - kv 13: tokenizer.ggml.token_type arr
llama_model_loader: - kv 14: tokenizer.ggml.merges arr
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32
llama_model_loader: - kv 18: general.quantization_version u32
llama_model_loader: - type f32: 322 tensors
llama_model_loader: - type q4_K: 102 tensors
llama_model_loader: - type q5_K: 40 tensors
llama_model_loader: - type q6_K: 21 tensors
error loading model: invalid character
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '..\models\me\sqlcoder.Q4_K_M\sqlcoder.Q4_K_M.gguf'
main: error: unable to load model