output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
GGUF division-by-zero loader crash PoC
This repository contains a malformed GGUF file that triggers sanitizer-backed undefined behavior during llama.cpp model loading.
PoC file: poc_gguf_divzero_alignment_loader_crash.gguf
SHA256: a0df9cbeba1fb33b95fbd8b4dd7b403a5da25c4c9ee1649674f9344f55c1f593
Size: 2387040 bytes
Reproduce: LLAMA_CLI=/path/to/llama-cli bash reproduce.sh
Expected:
- runtime error: division by zero
- AddressSanitizer: FPE
- abnormal process termination
Boundary: This is not RCE. This is malformed GGUF model-file-triggered undefined behavior and loader crash.
- Downloads last month
- 131
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="AM-Core/gguf-divzero-loader-crash-poc-clean", filename="poc_gguf_divzero_alignment_loader_crash.gguf", )