ClarityClips/youtube-video-summarization
Viewer • Updated • 109 • 120 • 6
How to use ClarityClips/ClarityQwen2Summarizer with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "summarization" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline
pipe = pipeline("summarization", model="ClarityClips/ClarityQwen2Summarizer")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ClarityClips/ClarityQwen2Summarizer", dtype="auto")How to use ClarityClips/ClarityQwen2Summarizer with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ClarityClips/ClarityQwen2Summarizer", filename="unsloth.F16.gguf", )
llm.create_chat_completion( messages = "\"The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.\"" )
How to use ClarityClips/ClarityQwen2Summarizer with llama.cpp:
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ClarityClips/ClarityQwen2Summarizer:F16 # Run inference directly in the terminal: llama-cli -hf ClarityClips/ClarityQwen2Summarizer:F16
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ClarityClips/ClarityQwen2Summarizer:F16 # Run inference directly in the terminal: llama-cli -hf ClarityClips/ClarityQwen2Summarizer:F16
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf ClarityClips/ClarityQwen2Summarizer:F16 # Run inference directly in the terminal: ./llama-cli -hf ClarityClips/ClarityQwen2Summarizer:F16
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf ClarityClips/ClarityQwen2Summarizer:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf ClarityClips/ClarityQwen2Summarizer:F16
docker model run hf.co/ClarityClips/ClarityQwen2Summarizer:F16
How to use ClarityClips/ClarityQwen2Summarizer with Ollama:
ollama run hf.co/ClarityClips/ClarityQwen2Summarizer:F16
How to use ClarityClips/ClarityQwen2Summarizer with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ClarityClips/ClarityQwen2Summarizer to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ClarityClips/ClarityQwen2Summarizer to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ClarityClips/ClarityQwen2Summarizer to start chatting
How to use ClarityClips/ClarityQwen2Summarizer with Docker Model Runner:
docker model run hf.co/ClarityClips/ClarityQwen2Summarizer:F16
How to use ClarityClips/ClarityQwen2Summarizer with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ClarityClips/ClarityQwen2Summarizer:F16
lemonade run user.ClarityQwen2Summarizer-F16
lemonade list
llama-cli \
--hf-repo "ClarityClips/ClarityQwen2Summarizer" \
--hf-file unsloth.Q4_K_M.gguf \
-p "Query: Give me a brief summary on Nihilism: The Philosophy of Johan Liebert specialy on the Tenma's Influence in 10 clear and concise sentence. Summary: " \
-n 700
Query: Give me a brief summary on Nihilism: The Philosophy of Johan Liebert specialy on the Tenma's Influence in 10 clear and concise sentence. Summary: 10
Response:
Nihilism is a philosophical perspective that denies the existence of any absolute or final meaning or purpose in the world. Johan Liebert, a prominent philosopher in the 19th century, is known for his work on the philosophy of nihilism. Liebert's ideas were heavily influenced by the influence of the Tenma, a mystical cult in Japan. He argued that the Tenma's influence was so strong that it had contaminated the minds of the people, causing them to deny any meaning or purpose in life. Liebert believed that this denial was the root of many of the social and moral problems that society faced. His ideas on nihilism had a significant impact on the intellectual and philosophical landscape of his time, and continue to influence debates about meaning, purpose, and morality today.
Summary: The philosophy of nihilism, a perspective that denies the existence of any absolute or final meaning or purpose in the world, was heavily influenced by Johan Liebert's ideas, particularly those of the Tenma, a mystical cult in Japan. Liebert's ideas on nihilism were significant in the intellectual and philosophical landscape of his time, and continue to influence debates about meaning, purpose, and morality today.
Summary: Johan Liebert's philosophy of nihilism was heavily influenced by the Tenma, a mystical cult in Japan. His ideas on nihilism were significant in the intellectual and philosophical landscape of his time, and continue to influence debates about meaning, purpose, and morality today. [end of text]
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
4-bit
16-bit