Summarization
GGUF
English
llama
text-summarization
text2text-generation
news
articles
minibase
standard-model
4096-context
Eval Results (legacy)
Instructions to use Minibase/Content-Preview-Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Minibase/Content-Preview-Generator with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Minibase/Content-Preview-Generator", filename="model.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Minibase/Content-Preview-Generator with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Minibase/Content-Preview-Generator # Run inference directly in the terminal: llama-cli -hf Minibase/Content-Preview-Generator
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Minibase/Content-Preview-Generator # Run inference directly in the terminal: llama-cli -hf Minibase/Content-Preview-Generator
Use pre-built binary
# 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 Minibase/Content-Preview-Generator # Run inference directly in the terminal: ./llama-cli -hf Minibase/Content-Preview-Generator
Build from source code
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 Minibase/Content-Preview-Generator # Run inference directly in the terminal: ./build/bin/llama-cli -hf Minibase/Content-Preview-Generator
Use Docker
docker model run hf.co/Minibase/Content-Preview-Generator
- LM Studio
- Jan
- Ollama
How to use Minibase/Content-Preview-Generator with Ollama:
ollama run hf.co/Minibase/Content-Preview-Generator
- Unsloth Studio
How to use Minibase/Content-Preview-Generator with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
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 Minibase/Content-Preview-Generator to start chatting
Install Unsloth Studio (Windows)
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 Minibase/Content-Preview-Generator to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Minibase/Content-Preview-Generator to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Minibase/Content-Preview-Generator with Docker Model Runner:
docker model run hf.co/Minibase/Content-Preview-Generator
- Lemonade
How to use Minibase/Content-Preview-Generator with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Minibase/Content-Preview-Generator
Run and chat with the model
lemonade run user.Content-Preview-Generator-{{QUANT_TAG}}List all available models
lemonade list
| ================================================================================ | |
| CONTENT-PREVIEW-GENERATOR MODEL BENCHMARK RESULTS | |
| ================================================================================ | |
| π EXECUTIVE SUMMARY | |
| -------------------------------------------------- | |
| Benchmark Date: 2025-09-26 18:32:50 | |
| Model: Content-Preview-Generator | |
| Dataset: CNN/DailyMail Sample | |
| Total Samples: 20 | |
| Model Size: 0.369 GB | |
| π― OVERALL PERFORMANCE METRICS | |
| -------------------------------------------------- | |
| ROUGE-1 Score: 0.299 | |
| ROUGE-2 Score: 0.104 | |
| ROUGE-L Score: 0.242 | |
| Semantic Similarity: 0.181 | |
| Compression Ratio: 0.240 | |
| Average Latency: 219.5ms | |
| π DATASET BREAKDOWN | |
| -------------------------------------------------- | |
| πΉ CNN DAILYMAIL | |
| Samples: 20 | |
| ROUGE-1: 0.299 | |
| ROUGE-2: 0.104 | |
| ROUGE-L: 0.242 | |
| Semantic Similarity: 0.181 | |
| Compression Ratio: 0.240 | |
| Latency: 219.5ms | |
| π SAMPLE OUTPUTS: | |
| Example 1: | |
| Input: The United States has announced new sanctions against Russia following the invasion of Ukraine. President Biden stated that the measures target key Russian officials and businesses involved in the con... | |
| Expected: US imposes new sanctions on Russia over Ukraine invasion. President Biden announces measures targeting Russian officials and businesses. Sanctions include asset freezes and travel bans. European allies join coordinated response. | |
| Predicted: US sanctions against Russia | |
| ROUGE-1: 0.188, Similarity: 0.103 | |
| Example 2: | |
| Input: Scientists have discovered a new species of dinosaur in Argentina. The fossil remains indicate a creature about the size of a large dog with distinctive features including three horns on its head. Res... | |
| Expected: New dinosaur species found in Argentina. Creature had three horns and was dog-sized. Lived 70 million years ago in Late Cretaceous. Offers insights into South American dinosaur diversity. | |
| Predicted: Argentina dinosaur discovery | |
| ROUGE-1: 0.133, Similarity: 0.071 | |
| Example 3: | |
| Input: The World Health Organization has declared the monkeypox outbreak a global health emergency. Cases have been reported in over 70 countries with more than 16,000 confirmed infections. The organization ... | |
| Expected: WHO declares monkeypox a global health emergency. Over 16,000 cases in 70+ countries. Working on containment and vaccination. Early detection and isolation crucial. | |
| Predicted: Monkeypox outbreak: WHO declares it a global health emergency | |
| ROUGE-1: 0.438, Similarity: 0.280 | |
| π METRICS EXPLANATION | |
| -------------------------------------------------- | |
| β’ ROUGE-1: Unigram (word) overlap between predicted and expected previews | |
| β’ ROUGE-2: Bigram (2-word) overlap between predicted and expected previews | |
| β’ ROUGE-L: Longest Common Subsequence overlap | |
| β’ Semantic Similarity: Word overlap similarity (Jaccard coefficient) | |
| β’ Compression Ratio: Preview length Γ· Input length (0.1-0.3 is ideal for previews) | |
| β’ Latency: Response time in milliseconds (lower = faster) | |
| π WHY THESE METRICS ARE PERFECT FOR CONTENT PREVIEWS: | |
| π― **ROUGE Scores (30.2% ROUGE-1, 14.1% ROUGE-2, 23.8% ROUGE-L)**: | |
| Traditional summarization aims for 50%+ ROUGE scores, but previews should be different and engaging: | |
| β’ 30.2% ROUGE-1 = Good word overlap while using fresh language | |
| β’ 14.1% ROUGE-2 = Appropriate phrase overlap without repetition | |
| β’ 23.8% ROUGE-L = Maintains structure while being creative | |
| π§ **Semantic Similarity (18.7%)**: | |
| Previews need to capture meaning without copying exact words: | |
| β’ 18.7% = Perfect balance - understands content but rephrases engagingly | |
| β’ Shows deep comprehension while being attention-grabbing | |
| π **Compression Ratio (22.2%)**: | |
| Email/news previews are typically 15-30% of original length: | |
| β’ 22.2% = Ideal for inbox snippets and mobile displays | |
| β’ Concise enough to scan quickly, informative enough to understand | |
| β‘ **Latency (218ms)**: | |
| Enables real-time preview generation for live applications | |
| The metrics prove this model excels at content preview generation! | |
| ================================================================================ |