Instructions to use agk4444/sat-tutor-qwen2.5-7b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use agk4444/sat-tutor-qwen2.5-7b-gguf 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 agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf agk4444/sat-tutor-qwen2.5-7b-gguf: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 agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf agk4444/sat-tutor-qwen2.5-7b-gguf: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 agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M

Use Docker

docker model run hf.co/agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use agk4444/sat-tutor-qwen2.5-7b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "agk4444/sat-tutor-qwen2.5-7b-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "agk4444/sat-tutor-qwen2.5-7b-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M

Ollama
How to use agk4444/sat-tutor-qwen2.5-7b-gguf with Ollama:
```
ollama run hf.co/agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use agk4444/sat-tutor-qwen2.5-7b-gguf with Docker Model Runner:
```
docker model run hf.co/agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M
```

Lemonade

How to use agk4444/sat-tutor-qwen2.5-7b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull agk4444/sat-tutor-qwen2.5-7b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.sat-tutor-qwen2.5-7b-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

SAT Tutor - Qwen2.5-7B (GGUF Q4_K_M)

Developed by AGK FIRE INC.

A Qwen2.5-7B-Instruct fine-tune that tutors for the SAT (math + reading/writing), packaged as a Q4_K_M GGUF for local inference with llama.cpp, Ollama, LM Studio, and friends.

File: sat-tutor-qwen2.5-7b.Q4_K_M.gguf (~4.35 GB)
Format: GGUF V3, 339 tensors, 32k context length
Base model: Qwen/Qwen2.5-7B-Instruct
Adapter (pre-merge): agk4444/sat-tutor-qwen2.5-7b

What it does

Works through SAT questions step by step and finishes with a clear Answer: X line. Trained on SAT-style math and reading/writing questions with step-by-step solutions.

Held-out eval of the 15k tuned adapter (the GGUF is this adapter quantized; the file itself has not been re-evaluated):

Section	Parseable	Strict
Math	70/77 (90.9%)	70/100 (70%)
Reading/Writing	45/59 (76.3%)	45/60 (75%)

"Parseable" counts questions where the model emitted the expected Answer: X format; "strict" counts unparseable answers as wrong. Unparseable usually means a formatting miss rather than a wrong answer.

Usage

llama.cpp

./llama-cli -m sat-tutor-qwen2.5-7b.Q4_K_M.gguf -n 512 \
 -p "Solve step by step. If x + 5 = 12, what is x?"

Ollama

# Modelfile
FROM ./sat-tutor-qwen2.5-7b.Q4_K_M.gguf
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>{{ end }}<|im_start|>assistant
"""
PARAMETER stop "<|im_end|>"

ollama create sat-tutor -f Modelfile
ollama run sat-tutor

Running Ollama in Docker

docker run -d --name ollama -p 11434:11434 -v ollama:/root/.ollama ollama/ollama
docker cp sat-tutor-qwen2.5-7b.Q4_K_M.gguf ollama:/root/
docker cp Modelfile ollama:/root/
docker exec -w /root ollama ollama create sat-tutor -f Modelfile
docker exec ollama ollama run sat-tutor

LM Studio / GPT4All / text-generation-webui

Drop the .gguf into the app's models folder - it auto-detects the Qwen2 chat template.

Prompt format

ChatML (Qwen2.5-Instruct):

<|im_start|>system
You are a helpful SAT tutor.<|im_end|>
<|im_start|>user
Solve step by step. If x + 5 = 12, what is x?<|im_end|>
<|im_start|>assistant

The model is trained to reason step by step and end with Answer: X.

Training details

Base: Qwen2.5-7B-Instruct, 4-bit QLoRA
Data: ~15k SAT-style examples (random sample of a 31k pool), seq len 1024
Adapter merged into base weights (fp16), then quantized: fp16 -> Q8_0 -> Q4_K_M
Note: the planned 30k run (seq 2048, upsampled reading/writing) has not trained yet

Limitations

SAT-focused: off-topic questions get base-model-quality answers at best.
4-bit quantization trades a little accuracy for size; the fp16 merge is the full-quality reference.
It can still make mistakes - double-check the math against the steps shown.

License

Apache 2.0 (inherited from Qwen2.5).

Downloads last month: 152

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for agk4444/sat-tutor-qwen2.5-7b-gguf

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(428)

this model