# !pip install llama-cpp-python
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="tmnam20/codellama-13b-text2sql-gguf",
filename="ggml-model-q4_k_m.gguf",
)
output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)- Downloads last month
- -
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
# Gated model: Login with a HF token with gated access permission hf auth login