Instructions to use llmware/slim-summary-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-summary-tool with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmware/slim-summary-tool", device_map="auto")

llama-cpp-python

How to use llmware/slim-summary-tool with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/slim-summary-tool",
	filename="slim-summarize.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 llmware/slim-summary-tool with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf llmware/slim-summary-tool
# Run inference directly in the terminal:
llama cli -hf llmware/slim-summary-tool

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf llmware/slim-summary-tool
# Run inference directly in the terminal:
llama cli -hf llmware/slim-summary-tool

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 llmware/slim-summary-tool
# Run inference directly in the terminal:
./llama-cli -hf llmware/slim-summary-tool

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 llmware/slim-summary-tool
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/slim-summary-tool

Use Docker

docker model run hf.co/llmware/slim-summary-tool

LM Studio
Jan
Ollama
How to use llmware/slim-summary-tool with Ollama:
```
ollama run hf.co/llmware/slim-summary-tool
```

Unsloth Studio

How to use llmware/slim-summary-tool 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 llmware/slim-summary-tool 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 llmware/slim-summary-tool to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmware/slim-summary-tool to start chatting

Atomic Chat new
Docker Model Runner
How to use llmware/slim-summary-tool with Docker Model Runner:
```
docker model run hf.co/llmware/slim-summary-tool
```

Lemonade

How to use llmware/slim-summary-tool with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/slim-summary-tool

Run and chat with the model

lemonade run user.slim-summary-tool-{{QUANT_TAG}}

List all available models

lemonade list

doberst commited on Mar 21, 2024

Commit

c465619

verified ·

1 Parent(s): 453a395

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -9,8 +9,8 @@
  "description": "slim-summary is a function-calling model, fine-tuned to output structured dictionaries",
  "prompt_wrapper": "human_bot",
  "prompt_format": "<human> {context_passage} <summarize> {optional text to guide summary} {(optional target list size)} </summarize>\n<bot>:",
- "output_format": "{'summary': ['key point1', 'key point2', 'key point3', ...]}",
- "primary_keys": ["summary"],
  "output_values": ["list of summary points"],
  "publisher": "llmware",
  "release_date": "march 2024",

  "description": "slim-summary is a function-calling model, fine-tuned to output structured dictionaries",
  "prompt_wrapper": "human_bot",
  "prompt_format": "<human> {context_passage} <summarize> {optional text to guide summary} {(optional target list size)} </summarize>\n<bot>:",
+ "output_format": "['key point1', 'key point2', 'key point3', ...]",
+ "primary_keys": ["no primary key - returns a list, not dict"],
  "output_values": ["list of summary points"],
  "publisher": "llmware",
  "release_date": "march 2024",