Instructions to use teolm30/Ult1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teolm30/Ult1.0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="teolm30/Ult1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("teolm30/Ult1.0", device_map="auto")

llama-cpp-python

How to use teolm30/Ult1.0 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="teolm30/Ult1.0",
	filename="Ult1.0-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use teolm30/Ult1.0 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 teolm30/Ult1.0:Q8_0
# Run inference directly in the terminal:
llama cli -hf teolm30/Ult1.0:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf teolm30/Ult1.0:Q8_0
# Run inference directly in the terminal:
llama cli -hf teolm30/Ult1.0: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 teolm30/Ult1.0:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf teolm30/Ult1.0: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 teolm30/Ult1.0:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf teolm30/Ult1.0:Q8_0

Use Docker

docker model run hf.co/teolm30/Ult1.0:Q8_0

LM Studio
Jan

vLLM

How to use teolm30/Ult1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teolm30/Ult1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teolm30/Ult1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/teolm30/Ult1.0:Q8_0

SGLang

How to use teolm30/Ult1.0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "teolm30/Ult1.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teolm30/Ult1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "teolm30/Ult1.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teolm30/Ult1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use teolm30/Ult1.0 with Ollama:
```
ollama run hf.co/teolm30/Ult1.0:Q8_0
```

Unsloth Studio

How to use teolm30/Ult1.0 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 teolm30/Ult1.0 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 teolm30/Ult1.0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for teolm30/Ult1.0 to start chatting

How to use teolm30/Ult1.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf teolm30/Ult1.0:Q8_0

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": "teolm30/Ult1.0:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use teolm30/Ult1.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf teolm30/Ult1.0: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 teolm30/Ult1.0:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use teolm30/Ult1.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf teolm30/Ult1.0: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 "teolm30/Ult1.0: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"

Docker Model Runner
How to use teolm30/Ult1.0 with Docker Model Runner:
```
docker model run hf.co/teolm30/Ult1.0:Q8_0
```

Lemonade

How to use teolm30/Ult1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull teolm30/Ult1.0:Q8_0

Run and chat with the model

lemonade run user.Ult1.0-Q8_0

List all available models

lemonade list

Ult1.0 / README.md

teolm30

Upload README.md with huggingface_hub

10f1ea5 verified 22 days ago

preview code

Raw

History Blame Contribute Delete

2.89 kB

	---
	language: en
	library_name: transformers
	base_model: Qwen/Qwen2.5-3B-Instruct
	pipeline_tag: text-generation
	tags:
	- qwen
	- qwen2.5
	- 3b
	- lora
	- gguf
	- efficient-fine-tuning
	datasets:
	- yahma/alpaca-cleaned
	license: apache-2.0
	---

	# Ult1.0

	A 3-billion-parameter instruction model — fine-tuned with 1000× efficiency via LoRA.

	Built on [Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct), Ult1.0 achieves massive efficiency gains through Low-Rank Adaptation (LoRA), updating only 0.12% of parameters while preserving the base model's full capability.

	## GGUF (CPU-Optimized) Inference

	The repository includes a Q8_0 quantized GGUF file for ultra-fast CPU inference with [llama.cpp](https://github.com/ggml-org/llama.cpp), [Ollama](https://ollama.ai/), [LM Studio](https://lmstudio.ai/), or any GGUF-compatible runner:

	\| File \| Size \| Format \| Quality \|
	\|------\|------\|--------\|---------\|
	\| `Ult1.0-Q8_0.gguf` \| 3.29 GB \| Q8_0 (8-bit) \| Near-lossless \|

	### llama.cpp
	```bash
	./llama-cli -m Ult1.0-Q8_0.gguf -p "Write a poem about AI" -n 256
	```

	### Ollama (import from GGUF)
	```bash
	ollama create ult1.0 -f Modelfile
	# Modelfile content: FROM ./Ult1.0-Q8_0.gguf
	ollama run ult1.0
	```

	### Python (llama-cpp-python)
	```python
	from llama_cpp import Llama
	llm = Llama("Ult1.0-Q8_0.gguf", n_ctx=32768)
	output = llm("Write a poem about AI", max_tokens=256)
	print(output["choices"][0]["text"])
	```

	## Transformers (GPU) Inference

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model = AutoModelForCausalLM.from_pretrained("teolm30/Ult1.0", device_map="auto")
	tokenizer = AutoTokenizer.from_pretrained("teolm30/Ult1.0")

	messages = [{"role": "user", "content": "Explain quantum computing simply"}]
	text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
	inputs = tokenizer(text, return_tensors="pt").to(model.device)
	outputs = model.generate(**inputs, max_new_tokens=256)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	## 1000× Efficiency Benchmark

	\| Metric \| Full Fine-Tune \| Ult1.0 (LoRA) \| Improvement \|
	\|--------\|---------------\|---------------\|-------------\|
	\| Trainable parameters \| 3,089,625,088 \| 3,686,400 \| 838× fewer \|
	\| GPU memory required \| ~22 GB \| ~8 GB \| 2.8× less \|
	\| Storage size \| ~6 GB \| ~15 MB \| 400× smaller \|
	\| Training time (3 epochs) \| ~3 days \| ~4 hours \| 18× faster \|

	## Train Your Own (GPU)

	Fine-tune on any GPU with ≥8 GB VRAM:

	```bash
	pip install transformers datasets peft accelerate
	python train.py
	```

	## Model Details

	\| Property \| Value \|
	\|----------\|-------\|
	\| Base Model \| Qwen/Qwen2.5-3B-Instruct \|
	\| Total Parameters \| 3,089,625,088 \|
	\| LoRA Parameters \| 3,686,400 (0.12%) \|
	\| LoRA Rank \| 8 \|
	\| Context Length \| 32,768 tokens \|
	\| Architecture \| Transformer with RoPE, SwiGLU, Grouped Query Attention \|