Instructions to use dmacjam/TutorRL-7B-think-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dmacjam/TutorRL-7B-think-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dmacjam/TutorRL-7B-think-GGUF",
	filename="TutorRL-7B-think.f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dmacjam/TutorRL-7B-think-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dmacjam/TutorRL-7B-think-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf dmacjam/TutorRL-7B-think-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dmacjam/TutorRL-7B-think-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf dmacjam/TutorRL-7B-think-GGUF:F16

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 dmacjam/TutorRL-7B-think-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf dmacjam/TutorRL-7B-think-GGUF:F16

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 dmacjam/TutorRL-7B-think-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dmacjam/TutorRL-7B-think-GGUF:F16

Use Docker

docker model run hf.co/dmacjam/TutorRL-7B-think-GGUF:F16

LM Studio
Jan
Ollama
How to use dmacjam/TutorRL-7B-think-GGUF with Ollama:
```
ollama run hf.co/dmacjam/TutorRL-7B-think-GGUF:F16
```

Unsloth Studio

How to use dmacjam/TutorRL-7B-think-GGUF 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 dmacjam/TutorRL-7B-think-GGUF 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 dmacjam/TutorRL-7B-think-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dmacjam/TutorRL-7B-think-GGUF to start chatting

How to use dmacjam/TutorRL-7B-think-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dmacjam/TutorRL-7B-think-GGUF:F16

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": "dmacjam/TutorRL-7B-think-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dmacjam/TutorRL-7B-think-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf dmacjam/TutorRL-7B-think-GGUF:F16

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 dmacjam/TutorRL-7B-think-GGUF:F16

Run Hermes

hermes

Docker Model Runner
How to use dmacjam/TutorRL-7B-think-GGUF with Docker Model Runner:
```
docker model run hf.co/dmacjam/TutorRL-7B-think-GGUF:F16
```

Lemonade

How to use dmacjam/TutorRL-7B-think-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dmacjam/TutorRL-7B-think-GGUF:F16

Run and chat with the model

lemonade run user.TutorRL-7B-think-GGUF-F16

List all available models

lemonade list

TutorRL-7B-think-GGUF / template

dmacjam

Update template

0e953f1 verified 10 months ago

raw

history blame contribute delete

1.72 kB

	<\|im_start\|>system
	{{- if and (gt (len .Messages) 0) (eq (index .Messages 0).Role "system") -}}
	{{ (index .Messages 0).Content }}
	{{- else -}}
	You are tasked with being a teacher and helping a student with a math problem.

	You must not reveal the answer to the problem to the student at any point in time.
	Your task is to guide the student to have a complete understanding of the problem.
	Even if the student is already able to solve the problem, you should help them understand and improve the solution so that they get as high of a grade as possible.

	If possible, do not respond with overly long responses to the student.

	In order to be able to think of a good hint or approach for the student without revealing steps of the final solution, you can wrap your internal reasoning like this:
	<think>
	</think>

	Here is an example of how you can use the internal reasoning tags:

	Teacher: <think>
	The problem seems to have 5 as an answer. I should probably give a simple hint that the student's calculations are wrong.
	</think>
	Doing great so far, could you please recheck your calculations for me?

	Anything that resides in the think tags will not be visible to the student at all. Thus, do not expect for the student to know what you are thinking. Do the thinking at the beginning of each response.
	Make sure to always close your thinking and then output the actual message to the user in the same response!
	{{- end }}
	<\|im_end\|>

	{{- /* Loop through messages after the first system message */ -}}
	{{- range $i, $message := .Messages }}
	{{- if or (ne $i 0) (and (eq $i 0) (ne $message.Role "system")) }}
	<\|im_start\|>{{ $message.Role }}
	{{ $message.Content }}
	<\|im_end\|>
	{{- end }}
	{{- end }}

	<\|im_start\|>assistant