ggml-org
Eval bug: llama_model_load: error loading model: error loading model hyperparameters: key not found in model: llama.context_length
Name and Version
python3 convert_lora_to_gguf.py /models/CodeLlama-13b-finetuned --base /models/CodeLlama-13b-Instruct-hf --outfile /models/CodeLlama-13b.gguf --outtype f32
INFO:gguf.gguf_writer:Writing the following files: INFO:gguf.gguf_writer:/models/CodeLlama-13b.gguf: n_tensors = 320, total_size = 104.9M Writing: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 105M/105M [00:00<00:00, 210Mbyte/s] INFO:lora-to-gguf:Model successfully exported to /models/CodeLlama-13b.gguf
root@7d293a7fbb1c:/app/llama.cpp# ./build/bin/llama-cli -m /models/CodeLlama-13b.gguf build: 5092 (d3bd7193) with cc (Debian 12.2.0-14) 12.2.0 for x86_64-linux-gnu main: llama backend init main: load the model and apply lora adapter, if any llama_model_loader: loaded meta data with 12 key-value pairs and 320 tensors from /models/CodeLlama-13b.gguf (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = adapter llama_model_loader: - kv 2: adapter.type str = lora llama_model_loader: - kv 3: general.name str = CodeLlama 13b Finetuned llama_model_loader: - kv 4: general.finetune str = finetuned llama_model_loader: - kv 5: general.basename str = CodeLlama llama_model_loader: - kv 6: general.size_label str = 13B llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = models/CodeLlama 13b Instruct Hf llama_model_loader: - kv 9: general.base_model.0.repo_url str = https://huggingface.co//models/CodeLl... llama_model_loader: - kv 10: adapter.lora.alpha f32 = 32.000000 llama_model_loader: - kv 11: general.quantization_version u32 = 2 llama_model_loader: - type f32: 320 tensors print_info: file format = GGUF V3 (latest) print_info: file type = all F32 (guessed) print_info: file size = 100.00 MiB (32.00 BPW) llama_model_load: error loading model: error loading model hyperparameters: key not found in model: llama.context_length llama_model_load_from_file_impl: failed to load model common_init_from_params: failed to load model '/models/CodeLlama-13b.gguf' main: error: unable to load model
Operating systems
Linux
GGML backends
CPU
Hardware
cpu node cloud
Models
CodeLlama-13b-Instruct-hf
Problem description & steps to reproduce
What is the issue here?
First Bad Commit
No response
Relevant log output
NA
