output = llm(
"Once upon a time,",
max_tokens=512,
echo=True
)
print(output)π§ News-Intelligence Chatbot β GGUF λ²μ
μ΄ λͺ¨λΈμ Unslothλ₯Ό νμ©νμ¬
Colab νκ²½μμ μ§μ νμΈνλ(finetuning) ν
GGUF ν¬λ§·μΌλ‘ λ³νλ λλ©μΈ νΉν LLMμ
λλ€.
λ΄μ€Β·μ μ±
Β·μμ¬ λΆμμ μ΅μ νλ Alpaca Prompt κΈ°λ° Instruction LLMμΌλ‘,
μ λ¬Έμ μΈ μ 보λ₯Ό κΉμ΄ μκ² μ΄ν΄νκ³ λ΅λ³νλλ‘ νλλμμ΅λλ€.
π GitHub Repository
π μ¬κΈ°λ₯Ό ν΄λ¦νλ©΄ μ 체 νλ‘μ νΈλ‘ μ΄λν©λλ€
(λͺ¨λΈ νμΌ / νμ΅ μ½λ / Colab λ
ΈνΈλΆ ν¬ν¨)
π Dataset Link
Example usage:
- For text only LLMs: llama-cli --hf repo_id/model_name -p "why is the sky blue?"
- For multimodal models: llama-mtmd-cli -m model_name.gguf --mmproj mmproj_file.gguf
Available Model files:
meta-llama-3.1-8b.Q5_K_M.ggufmeta-llama-3.1-8b.Q8_0.ggufmeta-llama-3.1-8b.Q4_K_M.gguf
- Downloads last month
- 23
Hardware compatibility
Log In to add your hardware
4-bit
5-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="HaGPT/news-intelligence-chatbot", filename="", )