Uploaded model
- Developed by: Mollel
- License: apache-2.0
- Finetuned from model : gemma-7b-bnb-4bit
from llama_index.llms.huggingface import HuggingFaceLLM
llm = HuggingFaceLLM(
context_window=4096,
max_new_tokens=256,
generate_kwargs={"temperature": 0.7, "do_sample": False},
tokenizer_name="Mollel/Swahili_Gemma",
model_name="Mollel/Swahili_Gemma",
device_map="auto",
stopping_ids=[50278, 50279, 50277, 1, 0],
tokenizer_kwargs={"max_length": 4096},
model_kwargs={"torch_dtype": torch.float16}
)
Examples