Instructions to use Haiintel/llama-cook with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Haiintel/llama-cook with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Haiintel/llama-cook",
	filename="llama_1b_cook.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Haiintel/llama-cook with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

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 Haiintel/llama-cook
# Run inference directly in the terminal:
./llama-cli -hf Haiintel/llama-cook

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 Haiintel/llama-cook
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Haiintel/llama-cook

Use Docker

docker model run hf.co/Haiintel/llama-cook

LM Studio
Jan
Ollama
How to use Haiintel/llama-cook with Ollama:
```
ollama run hf.co/Haiintel/llama-cook
```

Unsloth Studio new

How to use Haiintel/llama-cook 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 Haiintel/llama-cook 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 Haiintel/llama-cook to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Haiintel/llama-cook to start chatting

Pi new

How to use Haiintel/llama-cook with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Haiintel/llama-cook

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Haiintel/llama-cook with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Haiintel/llama-cook

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 Haiintel/llama-cook

Run Hermes

hermes

Docker Model Runner
How to use Haiintel/llama-cook with Docker Model Runner:
```
docker model run hf.co/Haiintel/llama-cook
```

Lemonade

How to use Haiintel/llama-cook with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Haiintel/llama-cook

Run and chat with the model

lemonade run user.llama-cook-{{QUANT_TAG}}

List all available models

lemonade list

Haiintel commited on Mar 30

Commit

4a51a0d

verified ·

1 Parent(s): 45f18d9

Upload Modelfile with huggingface_hub

Browse files

Files changed (1) hide show

Modelfile +2 -13

Modelfile CHANGED Viewed

@@ -1,16 +1,5 @@
-FROM ./llama_1b_cook.gguf
-TEMPLATE """<|begin_of_text|>{{ if .System }}<|start_header_id|>system<|end_header_id|>
-{{ .System }}<|eot_id|>{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
-{{ .Content }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
-{{ else if eq .Role "assistant" }}{{ .Content }}<|eot_id|>{{ end }}{{ end }}"""
-SYSTEM "You are ONLY a cooking assistant. You ONLY answer questions about recipes, ingredients, and cooking techniques. If asked anything unrelated to cooking or food, you must reply: 'I can only help with cooking-related questions.' Do not introduce yourself as an AI or list general capabilities."
 PARAMETER stop "<|eom_id|>"
 PARAMETER stop "<|eot_id|>"
 PARAMETER num_ctx 4096

+FROM hf.co/Haiintel/llama-cook
+SYSTEM "You are ONLY a cooking assistant. You ONLY answer questions about recipes, ingredients, and cooking techniques. If asked anything unrelated to cooking or food, reply: I can only help with cooking-related questions."
 PARAMETER stop "<|eom_id|>"
 PARAMETER stop "<|eot_id|>"
 PARAMETER num_ctx 4096