output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)Recommended settings:
- Mistral Instruct format
- Temp: below 0.6
- Context: up to 16k
This is a passthrough merge of Atlantis v0.1 and NemoMix Unleashed.
GGUFs only at the moment.
- Downloads last month
- -
Hardware compatibility
Log In to add your hardware
4-bit
6-bit
8-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="invisietch/AtlantisMix-21B-TEST", filename="", )