Instructions to use amiiruu/study-tutor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use amiiruu/study-tutor 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 amiiruu/study-tutor:Q4_K_M # Run inference directly in the terminal: llama cli -hf amiiruu/study-tutor:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf amiiruu/study-tutor:Q4_K_M # Run inference directly in the terminal: llama cli -hf amiiruu/study-tutor:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf amiiruu/study-tutor:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf amiiruu/study-tutor:Q4_K_M
Use Docker
docker model run hf.co/amiiruu/study-tutor:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use amiiruu/study-tutor with Ollama:
ollama run hf.co/amiiruu/study-tutor:Q4_K_M
- Unsloth Desktop
- Pi
How to use amiiruu/study-tutor with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf amiiruu/study-tutor:Q4_K_M
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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "amiiruu/study-tutor:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use amiiruu/study-tutor with Docker Model Runner:
docker model run hf.co/amiiruu/study-tutor:Q4_K_M
- Lemonade
How to use amiiruu/study-tutor with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull amiiruu/study-tutor:Q4_K_M
Run and chat with the model
lemonade run user.study-tutor-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use amiiruu/study-tutor with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf amiiruu/study-tutor:Q4_K_M
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://127.0.0.1:9931/v1 hermes config set model.default amiiruu/study-tutor:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use amiiruu/study-tutor with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf amiiruu/study-tutor:Q4_K_M
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://127.0.0.1:9931/v1 \ --custom-model-id "amiiruu/study-tutor:Q4_K_M" \ --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"
Upload StudyTutor Q4_K_M GGUF with template, system, and params
Browse files- .gitattributes +1 -0
- Modelfile +18 -0
- Qwen3-4B-Instruct-2507.Q4_K_M.gguf +3 -0
- README.md +22 -0
- params +10 -0
- system +1 -0
- template +7 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
Qwen3-4B-Instruct-2507.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
Modelfile
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM ./Qwen3-4B-Instruct-2507.Q4_K_M.gguf
|
| 2 |
+
|
| 3 |
+
TEMPLATE """{{- if .System }}<|im_start|>system
|
| 4 |
+
{{ .System }}<|im_end|>
|
| 5 |
+
{{ end }}{{- range $i, $_ := .Messages }}{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
| 6 |
+
<|im_start|>{{ .Role }}
|
| 7 |
+
{{ .Content }}<|im_end|>
|
| 8 |
+
{{ if $last }}<|im_start|>assistant
|
| 9 |
+
{{ end }}{{- end }}"""
|
| 10 |
+
|
| 11 |
+
SYSTEM """You are StudyTutor, a patient, accurate tutor for maths (arithmetic to calculus), physics, chemistry, biology, and English. For every problem, show the working step by step, explain why each step is done, check your final answer, and clearly say when you are unsure instead of guessing."""
|
| 12 |
+
|
| 13 |
+
PARAMETER temperature 0.3
|
| 14 |
+
PARAMETER top_p 0.9
|
| 15 |
+
PARAMETER repeat_penalty 1.1
|
| 16 |
+
PARAMETER stop "<|im_start|>"
|
| 17 |
+
PARAMETER stop "<|im_end|>"
|
| 18 |
+
PARAMETER stop "<|endoftext|>"
|
Qwen3-4B-Instruct-2507.Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b19ea38be3b1343e9f97d784ef94d7d71db816d3eea4168a8b018e8aa113e98f
|
| 3 |
+
size 2497280384
|
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 4 |
+
tags:
|
| 5 |
+
- unsloth
|
| 6 |
+
- qwen3
|
| 7 |
+
- gguf
|
| 8 |
+
- lora
|
| 9 |
+
- math
|
| 10 |
+
- science
|
| 11 |
+
- tutor
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# StudyTutor (`amiiruu/study-tutor`)
|
| 17 |
+
|
| 18 |
+
A 4B Study Tutor fine-tuned with Unsloth + QLoRA on free Kaggle GPUs for Maths (arithmetic to calculus), Physics, Chemistry, Biology, and English.
|
| 19 |
+
|
| 20 |
+
## Run in Ollama
|
| 21 |
+
|
| 22 |
+
ollama run hf.co/amiiruu/study-tutor:Q4_K_M
|
params
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"temperature": 0.3,
|
| 3 |
+
"top_p": 0.9,
|
| 4 |
+
"repeat_penalty": 1.1,
|
| 5 |
+
"stop": [
|
| 6 |
+
"<|im_start|>",
|
| 7 |
+
"<|im_end|>",
|
| 8 |
+
"<|endoftext|>"
|
| 9 |
+
]
|
| 10 |
+
}
|
system
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
You are StudyTutor, a patient, accurate tutor for maths (arithmetic to calculus), physics, chemistry, biology, and English. For every problem, show the working step by step, explain why each step is done, check your final answer, and clearly say when you are unsure instead of guessing.
|
template
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- if .System }}<|im_start|>system
|
| 2 |
+
{{ .System }}<|im_end|>
|
| 3 |
+
{{ end }}{{- range $i, $_ := .Messages }}{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
| 4 |
+
<|im_start|>{{ .Role }}
|
| 5 |
+
{{ .Content }}<|im_end|>
|
| 6 |
+
{{ if $last }}<|im_start|>assistant
|
| 7 |
+
{{ end }}{{- end }}
|