Instructions to use vanpelt/summarizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vanpelt/summarizer with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vanpelt/summarizer",
	filename="gemma3-270m-summarizer-Q4_K_M.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.\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use vanpelt/summarizer with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vanpelt/summarizer:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vanpelt/summarizer:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vanpelt/summarizer:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf vanpelt/summarizer:Q4_K_M

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 vanpelt/summarizer:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf vanpelt/summarizer:Q4_K_M

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 vanpelt/summarizer:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vanpelt/summarizer:Q4_K_M

Use Docker

docker model run hf.co/vanpelt/summarizer:Q4_K_M

LM Studio
Jan
Ollama
How to use vanpelt/summarizer with Ollama:
```
ollama run hf.co/vanpelt/summarizer:Q4_K_M
```

Unsloth Studio new

How to use vanpelt/summarizer 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 vanpelt/summarizer 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 vanpelt/summarizer to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vanpelt/summarizer to start chatting

Docker Model Runner
How to use vanpelt/summarizer with Docker Model Runner:
```
docker model run hf.co/vanpelt/summarizer:Q4_K_M
```

Lemonade

How to use vanpelt/summarizer with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vanpelt/summarizer:Q4_K_M

Run and chat with the model

lemonade run user.summarizer-Q4_K_M

List all available models

lemonade list

vanpelt commited on Nov 14, 2025

Commit

59e78da

verified ·

1 Parent(s): bd35c35

Upload GGUF model

Browse files

Files changed (3) hide show

Modelfile +16 -0
gemma3-270m-synthetic-v11-Q4_K_M-unsloth.gguf +1 -1
model.safetensors +1 -1

Modelfile CHANGED Viewed

@@ -1,4 +1,19 @@
 FROM gemma3-270m-synthetic-v11-Q4_K_M-unsloth.gguf
 TEMPLATE """{{- $systemPromptAdded := false }}
 {{- range $i, $_ := .Messages }}
 {{- $last := eq (len (slice $.Messages $i)) 1 }}
@@ -16,6 +31,7 @@ TEMPLATE """{{- $systemPromptAdded := false }}
 {{- end }}
 {{- end }}
 """
 PARAMETER stop "<end_of_turn>"
 PARAMETER top_k 64
 PARAMETER top_p 0.95

 FROM gemma3-270m-synthetic-v11-Q4_K_M-unsloth.gguf
+# Default system prompt (used when user doesn't provide one)
+SYSTEM """
+You are a careful assistant that outputs ONLY valid JSON matching the schema:
+{
+  "summary": "<2-4 words, Title Case, no punctuation>",
+  "branch": "<kebab-case, lowercase, [a-z0-9-] only, max 3 words, prefix with a category like bug/, feat/, etc.>"
+}
+Never include explanations or extra keys.
+Turn this request for code changes into:
+1) a 2-4 word summary (Title Case),
+2) a friendly git branch name (prefixed kebab-case).
+"""
 TEMPLATE """{{- $systemPromptAdded := false }}
 {{- range $i, $_ := .Messages }}
 {{- $last := eq (len (slice $.Messages $i)) 1 }}
 {{- end }}
 {{- end }}
 """
 PARAMETER stop "<end_of_turn>"
 PARAMETER top_k 64
 PARAMETER top_p 0.95

gemma3-270m-synthetic-v11-Q4_K_M-unsloth.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c8076b50213fa57c1a26161b2b056c3c2c923bad6fa8faf5fd21666054e7dd
 size 253114720

 version https://git-lfs.github.com/spec/v1
+oid sha256:1945f31e71b83b6191d9b876290ac0b35ca759797451451459ebe00524fe3521
 size 253114720

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4cbd330f0f06961c32eb76e853b558ece07a9220eedd1e2328b40ba92daa56
 size 536223056

 version https://git-lfs.github.com/spec/v1
+oid sha256:f5fa9255bc20dd162e4a08dedcfbc190384c51295a1e640212a9cf8afc25c77e
 size 536223056