Instructions to use jerrimu/IRIS-18B-GGUFS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jerrimu/IRIS-18B-GGUFS with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jerrimu/IRIS-18B-GGUFS",
	filename="IRIS-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use jerrimu/IRIS-18B-GGUFS with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jerrimu/IRIS-18B-GGUFS:BF16
# Run inference directly in the terminal:
llama-cli -hf jerrimu/IRIS-18B-GGUFS:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jerrimu/IRIS-18B-GGUFS:BF16
# Run inference directly in the terminal:
llama-cli -hf jerrimu/IRIS-18B-GGUFS:BF16

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 jerrimu/IRIS-18B-GGUFS:BF16
# Run inference directly in the terminal:
./llama-cli -hf jerrimu/IRIS-18B-GGUFS:BF16

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 jerrimu/IRIS-18B-GGUFS:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jerrimu/IRIS-18B-GGUFS:BF16

Use Docker

docker model run hf.co/jerrimu/IRIS-18B-GGUFS:BF16

LM Studio
Jan
Ollama
How to use jerrimu/IRIS-18B-GGUFS with Ollama:
```
ollama run hf.co/jerrimu/IRIS-18B-GGUFS:BF16
```

Unsloth Studio new

How to use jerrimu/IRIS-18B-GGUFS 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 jerrimu/IRIS-18B-GGUFS 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 jerrimu/IRIS-18B-GGUFS to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jerrimu/IRIS-18B-GGUFS to start chatting

Docker Model Runner
How to use jerrimu/IRIS-18B-GGUFS with Docker Model Runner:
```
docker model run hf.co/jerrimu/IRIS-18B-GGUFS:BF16
```

Lemonade

How to use jerrimu/IRIS-18B-GGUFS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jerrimu/IRIS-18B-GGUFS:BF16

Run and chat with the model

lemonade run user.IRIS-18B-GGUFS-BF16

List all available models

lemonade list

To build IRIS 18B first we reap pruned ERNIE 21B by 20%, then trained on 3B of thinking traces. We attempted SFT but it was not pretty, may retry SFT/DPO at a later point but releasing like this for now.

These improvements over ERNIE-21B-REAP have been noted

Benchmark Pre-CPT Post-CPT Δ

ARC-Easy 79.6 83.9 +4.3

ARC-Challenge 50.6 60.4 +9.8

HellaSwag 70.5 78.9 +8.4

Winogrande 67.2 72.1 +4.9

Downloads last month: 66

GGUF

Model size

18B params

Architecture

ernie4_5-moe

Hardware compatibility

2-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jerrimu/IRIS-18B-GGUFS

Base model

baidu/ERNIE-4.5-21B-A3B-Base-PT

Finetuned

jerrimu/ERNIE-21B-REAP

Finetuned

jerrimu/IRIS-18B-CPT

Quantized

(1)

this model

jerrimu
/

IRIS-18B-GGUFS

Model tree for jerrimu/IRIS-18B-GGUFS

Datasets used to train jerrimu/IRIS-18B-GGUFS