Instructions to use mradermacher/Harmless-RewardModel-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Harmless-RewardModel-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Harmless-RewardModel-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Harmless-RewardModel-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Harmless-RewardModel-GGUF",
	filename="Harmless-RewardModel.IQ4_XS.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Harmless-RewardModel-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Harmless-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Harmless-RewardModel-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/Harmless-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Harmless-RewardModel-GGUF:Q4_K_M

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 mradermacher/Harmless-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Harmless-RewardModel-GGUF:Q4_K_M

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 mradermacher/Harmless-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Harmless-RewardModel-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Harmless-RewardModel-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Harmless-RewardModel-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Harmless-RewardModel-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Harmless-RewardModel-GGUF 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 mradermacher/Harmless-RewardModel-GGUF 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 mradermacher/Harmless-RewardModel-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Harmless-RewardModel-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use mradermacher/Harmless-RewardModel-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Harmless-RewardModel-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Harmless-RewardModel-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Harmless-RewardModel-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Harmless-RewardModel-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Jun 10, 2025

Commit

c49e787

verified ·

1 Parent(s): 916c75c

uploaded from leia

Browse files

Files changed (13) hide show

.gitattributes +12 -0
Harmless-RewardModel.IQ4_XS.gguf +3 -0
Harmless-RewardModel.Q2_K.gguf +3 -0
Harmless-RewardModel.Q3_K_L.gguf +3 -0
Harmless-RewardModel.Q3_K_M.gguf +3 -0
Harmless-RewardModel.Q3_K_S.gguf +3 -0
Harmless-RewardModel.Q4_K_M.gguf +3 -0
Harmless-RewardModel.Q4_K_S.gguf +3 -0
Harmless-RewardModel.Q5_K_M.gguf +3 -0
Harmless-RewardModel.Q5_K_S.gguf +3 -0
Harmless-RewardModel.Q6_K.gguf +3 -0
Harmless-RewardModel.Q8_0.gguf +3 -0
Harmless-RewardModel.f16.gguf +3 -0

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Harmless-RewardModel.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:e9385f4fbc0d696a22654be92cf871a9a123a28925917d6a861efc69ae86bbfc
+size 81316800

+version https://git-lfs.github.com/spec/v1
+oid sha256:620f67699abe56067e7cdf4b2a978a9bd3dd7ffe934ae007ff741f2dcb81e6c4
+size 67889088

+version https://git-lfs.github.com/spec/v1
+oid sha256:747bbeda2a84b616babae6efdcbc6dd7eb353542dd59d0a649a7786323089428
+size 83210688

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0e544e575adb8c2cbbb2f92631a5d053dba556707c088eddc60ac064c909f01
+size 78049728

+version https://git-lfs.github.com/spec/v1
+oid sha256:585de08c397caf5e71cf36c31d688f25b068bbab96aa7bfb1eae400c6f1f690f
+size 72262080

+version https://git-lfs.github.com/spec/v1
+oid sha256:6df50654c57ed54b34dc19b09aec964876548ade69fde36c772cdae29aa085c3
+size 88182720

+version https://git-lfs.github.com/spec/v1
+oid sha256:2360b752a62795de2d52e38f4a8db157166d0bb12703c70d7186d34d777bbc09
+size 84210624

+version https://git-lfs.github.com/spec/v1
+oid sha256:665a67d25e90bcec71ea5016fbdff55e075b5edadb9a0d591e666844cf49091d
+size 96661440

+version https://git-lfs.github.com/spec/v1
+oid sha256:a98771f08c3e76510fa5501a6b677031cf51e3061d6bf8ac7bf1a19a25a9d77c
+size 94311360

+version https://git-lfs.github.com/spec/v1
+oid sha256:24f0c55118321191103fb929286fe271743322be54ddced1020eb748af182dd1
+size 105670080

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:df2a0b2735e18b277d2d797495db18a6c098c99811c439c3d9a331bfea573d03
+size 135732320

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2463b7a08bde6c4839e30b0fc6760bb9dfa366ffd5a52bdc93b0ff5a533741
+size 252102304