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.
Checkpoint GGUFs
Q6 GGUFs and yaml config archives for various checkpoint model tests.
These merges are tests for Goetia & Asmodeus model series.
See https://huggingface.co/Naphula-Archives/ for more models and yaml configs
Update
The series continues with Checkpoints 72 and beyond (previously used A-Z), a series of merges made after patching a broken python library (which was causing mergekit failures)
The recent batch for April 2026 covers C72-84 (all della merges). These are now using IQ4_XS or Q4_0 rather than Q6_K for initial testing.
- C72, C73, and C79-81 were deleted. They did not do as well as the others.
- C74, C75, C76, C77, C78, C82, C83, and C84 are uploaded in GGUF format.
- Additionally there are seperate tests in progress for
qliphoth,karcher_stock, andaethermerge methods.
Most of these have not been tested throroughly and may exhibit unusual properties or occasional refusals.
- Downloads last month
- 1,411
Hardware compatibility
Log In to add your hardware
4-bit
6-bit
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="Naphula-Archives/Checkpoint-GGUFs", filename="", )