output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)Model Details
TEMPLATE:
<|system|> {system_message} <|user|> {prompt} <|assistant|>
SPECIAL_TOKENS = { "pad": "<|pad|>", "unk": "<|unk|>", "bos": "<|bos|>", "eos": "<|eos|>", "system": "<|system|>", "user": "<|user|>", "assistant": "<|assistant|>", "end": "<|end|>", "think": "<|think|>", "think_end": "<|think_end|>", "learn": "<|learn|>", }
- Downloads last month
- 4
Hardware compatibility
Log In to add your hardware
8-bit
16-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="xavuye/xavuye_model", filename="", )