Instructions to use RthItalia/AICE-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RthItalia/AICE-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RthItalia/AICE-v1",
	filename="mobile/AICE_v1_rwkv4_custom.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use RthItalia/AICE-v1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RthItalia/AICE-v1
# Run inference directly in the terminal:
llama-cli -hf RthItalia/AICE-v1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RthItalia/AICE-v1
# Run inference directly in the terminal:
llama-cli -hf RthItalia/AICE-v1

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 RthItalia/AICE-v1
# Run inference directly in the terminal:
./llama-cli -hf RthItalia/AICE-v1

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 RthItalia/AICE-v1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RthItalia/AICE-v1

Use Docker

docker model run hf.co/RthItalia/AICE-v1

LM Studio
Jan

vLLM

How to use RthItalia/AICE-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RthItalia/AICE-v1

Ollama
How to use RthItalia/AICE-v1 with Ollama:
```
ollama run hf.co/RthItalia/AICE-v1
```

Unsloth Studio new

How to use RthItalia/AICE-v1 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 RthItalia/AICE-v1 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 RthItalia/AICE-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RthItalia/AICE-v1 to start chatting

Docker Model Runner
How to use RthItalia/AICE-v1 with Docker Model Runner:
```
docker model run hf.co/RthItalia/AICE-v1
```

Lemonade

How to use RthItalia/AICE-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RthItalia/AICE-v1

Run and chat with the model

lemonade run user.AICE-v1-{{QUANT_TAG}}

List all available models

lemonade list

AICE-v1 Model Card

Overview

AICE-v1 is a compact conversational model in RWKV architecture, distributed as merged weights for text generation. AICE-v1 is a derivative model initialized from externally pre-trained foundation weights, then innovated with LoRA and merged for inference.

Technical profile

Architecture: RWKV causal language model
Layers: 24
Hidden size: 2048
Context length: 1024
Vocabulary size: 50277
Effective size: about 1.5B parameters
Primary format: model.safetensors (FP16/F32 mixed tensors, runtime friendly)

Training strategy

Initialization from pre-trained foundation checkpoint weights (third-party origin).
Instruction tuning performed with LoRA adapters.
Distilled supervision pipeline derived from a larger teacher model family (70B class).
LoRA adapters merged into a single consolidated model for inference.

Release intent

This repository contains the merged model artifacts for inference.
Adapter artifacts are optional internal training artifacts and are not required for runtime.

Suggested use

Assistant/chat inference
Lightweight deployment scenarios (desktop and mobile with quantized variants)
Prompt-based reasoning tasks

Limitations

Behavior quality depends on prompt design and decoding setup.
The model can still produce hallucinations and incorrect factual outputs.
Safety filtering and evaluation are required in production.

Runtime files

config.json
generation_config.json
tokenizer.json
tokenizer_config.json
special_tokens_map.json
model.safetensors

Mobile quantization

See MOBILE_Q4_PIPELINE.md for INT8/INT4 export and packaging.

Formats note

Included now: safetensors, ONNX (INT8, INT4) and GGUF.
GGUF artifact: aicemobile/AICE_v1_rwkv4_custom.gguf (custom RWKV4 GGUF layout).

Compliance documentation

EU AI Act public training-content summary: EU_TRAINING_SUMMARY.md

Downloads last month: 9

Safetensors

Model size

2B params

Tensor type

F32

F16