Instructions to use Susu11/new4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Susu11/new4b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "Susu11/new4b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Susu11/new4b 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 Susu11/new4b:Q8_0
# Run inference directly in the terminal:
llama cli -hf Susu11/new4b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Susu11/new4b:Q8_0
# Run inference directly in the terminal:
llama cli -hf Susu11/new4b:Q8_0

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 Susu11/new4b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Susu11/new4b:Q8_0

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 Susu11/new4b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Susu11/new4b:Q8_0

Use Docker

docker model run hf.co/Susu11/new4b:Q8_0

LM Studio
Jan

vLLM

How to use Susu11/new4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Susu11/new4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Susu11/new4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Susu11/new4b:Q8_0

Ollama
How to use Susu11/new4b with Ollama:
```
ollama run hf.co/Susu11/new4b:Q8_0
```
Unsloth Desktop

How to use Susu11/new4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Susu11/new4b:Q8_0

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": "Susu11/new4b:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Susu11/new4b with Docker Model Runner:
```
docker model run hf.co/Susu11/new4b:Q8_0
```

Lemonade

How to use Susu11/new4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Susu11/new4b:Q8_0

Run and chat with the model

lemonade run user.new4b-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Susu11/new4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Susu11/new4b:Q8_0

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 Susu11/new4b:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Susu11/new4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Susu11/new4b:Q8_0

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 "Susu11/new4b:Q8_0" \
  --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"

Susu11/new4b

QLoRA adapters for a Grade 10 Socratic science tutor on Qwen/Qwen3-4B-Instruct-2507.

This Hub repo is Qwen-only. Phi-3 adapters live in a separate model repo (HF_HUB_REPO). GitHub Sushey01/Socratic-Model-Fine-Tune holds code and JSONL; this repo holds weights.

What is uploaded

Path	Contents
Repo root	Final PEFT adapters + tokenizer after SFT
`gguf/`	Optional Q8_0/F16 GGUF after `python start.py --gguf --qwen`

Trainer checkpoint-* folders stay on the training PC (socratic_qwen3_v9_model/) and are not uploaded.

Base model

Instruct / non-thinking checkpoint only (no <think> blocks).
Do not load these adapters on Qwen3-4B-Thinking-2507.

Train (QLoRA)

4-bit NF4 + LoRA (r=8, alpha=16) via python start.py --qwen → train_qwen.py. Data: Susu11/socraticfinetune.

Deploy (Python / GPU)

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "Susu11/new4b"
tok = AutoTokenizer.from_pretrained(adapter, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
)
model = PeftModel.from_pretrained(model, adapter)
messages = [
    {"role": "system", "content": "You are a Socratic Science Tutor for a Grade 10 student. Never give the final answer directly."},
    {"role": "user", "content": "Why does ice float?"},
]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128, do_sample=False)
print(tok.decode(out[0, inputs.input_ids.shape[-1]:], skip_special_tokens=True))

Local helper: uv run python infer_qwen.py after adapters exist.

Deploy (llama.cpp / Ollama)

After merge + convert: python start.py --gguf --qwen. Then point llama.cpp or Ollama at gguf/socratic-qwen3-q8_0.gguf on this repo.

Eval

Same ScienceQA 256-item slice as Phi-3: python start.py --eval --qwen. Compare eval/scienceqa_acc and eval/scienceqa_sri in W&B project science_socratic_qwen3-4b_instruct (WANDB_PROJECT_QWEN).

Downloads last month: 53

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

8-bit

Model tree for Susu11/new4b

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5722)

this model