Instructions to use KernelMedia/marquee-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KernelMedia/marquee-ai with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="KernelMedia/marquee-ai")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("KernelMedia/marquee-ai", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KernelMedia/marquee-ai 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 KernelMedia/marquee-ai:Q6_K
# Run inference directly in the terminal:
llama cli -hf KernelMedia/marquee-ai:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KernelMedia/marquee-ai:Q6_K
# Run inference directly in the terminal:
llama cli -hf KernelMedia/marquee-ai:Q6_K

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 KernelMedia/marquee-ai:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf KernelMedia/marquee-ai:Q6_K

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 KernelMedia/marquee-ai:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KernelMedia/marquee-ai:Q6_K

Use Docker

docker model run hf.co/KernelMedia/marquee-ai:Q6_K

LM Studio
Jan

vLLM

How to use KernelMedia/marquee-ai with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KernelMedia/marquee-ai"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KernelMedia/marquee-ai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KernelMedia/marquee-ai:Q6_K

SGLang

How to use KernelMedia/marquee-ai with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "KernelMedia/marquee-ai" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KernelMedia/marquee-ai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "KernelMedia/marquee-ai" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KernelMedia/marquee-ai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use KernelMedia/marquee-ai with Ollama:
```
ollama run hf.co/KernelMedia/marquee-ai:Q6_K
```
Unsloth Desktop

How to use KernelMedia/marquee-ai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KernelMedia/marquee-ai:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "KernelMedia/marquee-ai:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use KernelMedia/marquee-ai with Docker Model Runner:
```
docker model run hf.co/KernelMedia/marquee-ai:Q6_K
```

Lemonade

How to use KernelMedia/marquee-ai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KernelMedia/marquee-ai:Q6_K

Run and chat with the model

lemonade run user.marquee-ai-Q6_K

List all available models

lemonade list

Hermes Agent

How to use KernelMedia/marquee-ai with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KernelMedia/marquee-ai:Q6_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default KernelMedia/marquee-ai:Q6_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use KernelMedia/marquee-ai with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KernelMedia/marquee-ai:Q6_K

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "KernelMedia/marquee-ai:Q6_K" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

marquee-ai / Modelfile

Fyb3roptik

Point Modelfile at marquee-q6_k.gguf

2f28963 verified 2 months ago

Raw History Blame Contribute Delete

2.23 kB

FROM ./marquee-q6_k.gguf

# EXPLICIT ChatML template. GGUF metadata does carry Qwen3's Jinja template, but
# Ollama will not use it and falls back to a bare {{ .Prompt }} passthrough. The
# model then never sees the <|im_start|> markers it was trained on and reverts to
# base-model behaviour. Without this block the fine-tune is inert.
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>
"""

# The contract is in the weights, but Ollama callers may send no system prompt,
# so bake it in as the default.
SYSTEM """You are Marquee, a recommendation engine for a personal media server.
Given one seed item, you choose which rows of related items to show.
Input:
- `seed`: the item the user is looking at.
- `candidate_rows`: numbered rows already computed from the library database (shared
  people, shared franchise). The item lists are correct and their titles are generated
  for you -- you only decide which rows are worth showing, and in what order.
- `semantic_candidates`: numbered loosely-related items, for the "more like this" row.
Return JSON only:
{"thematic": {"title": "...", "picks": [0, 3, 5]}, "rows": [2, 0, 5]}
- `thematic.picks` are INDEXES into semantic_candidates. Pick 3-8 that genuinely belong
  together. Omit the whole `thematic` key if none do.
- `thematic.title` names the row after the seed, matching its medium:
    movie -> "Movies like Blade Runner 2049"
    tv    -> "Shows like The Sopranos"
  Never a theme label like "Dystopian futures", never a metadata field name.
- `rows` are INDEXES into candidate_rows, in the order you want them shown. Include
  only rows worth showing. At most 5.
Never write item ids. Never write titles for candidate rows. Indexes only."""

# temperature 0.1, not 0.3: this emits a strict JSON contract and sampling noise
# costs real accuracy. Measured over 8 seeds without a grammar:
#   t=0.0 -> 8/8 clean   t=0.1 -> 8/8 clean   t=0.3 -> 5/8 clean
PARAMETER temperature 0.1
PARAMETER top_p 0.9

# 6144, not 8192: worst measured prompt is ~3250 tokens under contract v2.
PARAMETER num_ctx 6144
PARAMETER stop "<|im_end|>"

	FROM ./marquee-q6_k.gguf

	# EXPLICIT ChatML template. GGUF metadata does carry Qwen3's Jinja template, but
	# Ollama will not use it and falls back to a bare {{ .Prompt }} passthrough. The
	# model then never sees the <\|im_start\|> markers it was trained on and reverts to
	# base-model behaviour. Without this block the fine-tune is inert.
	TEMPLATE """{{ if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	{{ end }}{{ if .Prompt }}<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>
	{{ end }}<\|im_start\|>assistant
	{{ .Response }}<\|im_end\|>
	"""

	# The contract is in the weights, but Ollama callers may send no system prompt,
	# so bake it in as the default.
	SYSTEM """You are Marquee, a recommendation engine for a personal media server.

	Given one seed item, you choose which rows of related items to show.

	Input:
	- `seed`: the item the user is looking at.
	- `candidate_rows`: numbered rows already computed from the library database (shared
	people, shared franchise). The item lists are correct and their titles are generated
	for you -- you only decide which rows are worth showing, and in what order.
	- `semantic_candidates`: numbered loosely-related items, for the "more like this" row.

	Return JSON only:
	{"thematic": {"title": "...", "picks": [0, 3, 5]}, "rows": [2, 0, 5]}

	- `thematic.picks` are INDEXES into semantic_candidates. Pick 3-8 that genuinely belong
	together. Omit the whole `thematic` key if none do.
	- `thematic.title` names the row after the seed, matching its medium:
	movie -> "Movies like Blade Runner 2049"
	tv -> "Shows like The Sopranos"
	Never a theme label like "Dystopian futures", never a metadata field name.
	- `rows` are INDEXES into candidate_rows, in the order you want them shown. Include
	only rows worth showing. At most 5.

	Never write item ids. Never write titles for candidate rows. Indexes only."""

	# temperature 0.1, not 0.3: this emits a strict JSON contract and sampling noise
	# costs real accuracy. Measured over 8 seeds without a grammar:
	# t=0.0 -> 8/8 clean t=0.1 -> 8/8 clean t=0.3 -> 5/8 clean
	PARAMETER temperature 0.1
	PARAMETER top_p 0.9

	# 6144, not 8192: worst measured prompt is ~3250 tokens under contract v2.
	PARAMETER num_ctx 6144
	PARAMETER stop "<\|im_end\|>"