How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jerrimu/IRIS-18B-GGUFS:# Run inference directly in the terminal:
llama-cli -hf jerrimu/IRIS-18B-GGUFS: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:# Run inference directly in the terminal:
./llama-cli -hf jerrimu/IRIS-18B-GGUFS: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:# Run inference directly in the terminal:
./build/bin/llama-cli -hf jerrimu/IRIS-18B-GGUFS:Use Docker
docker model run hf.co/jerrimu/IRIS-18B-GGUFS:Quick Links
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
- 57
Hardware compatibility
Log In to add your hardware
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
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf jerrimu/IRIS-18B-GGUFS:# Run inference directly in the terminal: llama-cli -hf jerrimu/IRIS-18B-GGUFS: