Instructions to use prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF",
	filename="GRAM-LLaMA3.2-3B-RewardModel.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 prithivMLmods/GRAM-LLaMA3.2-3B-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 prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/GRAM-LLaMA3.2-3B-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 prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/GRAM-LLaMA3.2-3B-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 prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/GRAM-LLaMA3.2-3B-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 prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M
```

Unsloth Studio new

How to use prithivMLmods/GRAM-LLaMA3.2-3B-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 prithivMLmods/GRAM-LLaMA3.2-3B-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 prithivMLmods/GRAM-LLaMA3.2-3B-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 prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF to start chatting

Pi new

How to use prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M

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": "prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M

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 prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.GRAM-LLaMA3.2-3B-RewardModel-GGUF-Q4_K_M

List all available models

lemonade list

GRAM-LLaMA3.2-3B-RewardModel-GGUF

GRAM-LLaMA3.2-3B-RewardModel is a generative reward model fine-tuned from the Llama-3.2-3B-Instruct base model released by NiuTrans. It is designed to improve reward generalization for large language models (LLMs) by leveraging a novel training approach that first pre-trains on large unlabeled datasets and then fine-tunes using supervised labeled data. The training uses label smoothing and optimizes a regularized ranking loss, bridging generative and discriminative reward modeling techniques. This enables the model to be applied flexibly across a variety of tasks without the usual need for extensive fine-tuning on task-specific datasets.

GRAM-LLaMA3.2-3B-RewardModel is evaluated on the JudgeBench benchmark, which covers domains such as Chat, Code, Math, and Safety. It achieves a competitive average score of 69.9 across these categories, demonstrating strong capability for use as an open-source plug-and-play reward model that can align LLMs effectively without retraining reward models from scratch. The repository includes usage examples that let users directly apply this reward model for assessing and ranking the quality of AI-generated responses in an impartial manner.

Model Files

Model File name	Size	QuantType
GRAM-LLaMA3.2-3B-RewardModel.BF16.gguf	6.43 GB	BF16
GRAM-LLaMA3.2-3B-RewardModel.F16.gguf	6.43 GB	F16
GRAM-LLaMA3.2-3B-RewardModel.F32.gguf	12.9 GB	F32
GRAM-LLaMA3.2-3B-RewardModel.Q2_K.gguf	1.36 GB	Q2_K
GRAM-LLaMA3.2-3B-RewardModel.Q3_K_L.gguf	1.82 GB	Q3_K_L
GRAM-LLaMA3.2-3B-RewardModel.Q3_K_M.gguf	1.69 GB	Q3_K_M
GRAM-LLaMA3.2-3B-RewardModel.Q3_K_S.gguf	1.54 GB	Q3_K_S
GRAM-LLaMA3.2-3B-RewardModel.Q4_K_M.gguf	2.02 GB	Q4_K_M
GRAM-LLaMA3.2-3B-RewardModel.Q4_K_S.gguf	1.93 GB	Q4_K_S
GRAM-LLaMA3.2-3B-RewardModel.Q5_K_M.gguf	2.32 GB	Q5_K_M
GRAM-LLaMA3.2-3B-RewardModel.Q5_K_S.gguf	2.27 GB	Q5_K_S
GRAM-LLaMA3.2-3B-RewardModel.Q6_K.gguf	2.64 GB	Q6_K
GRAM-LLaMA3.2-3B-RewardModel.Q8_0.gguf	3.42 GB	Q8_0

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

Downloads last month: 7

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW

Text Ranking

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

Model tree for prithivMLmods/GRAM-LLaMA3.2-3B-RewardModel-GGUF

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

NiuTrans/GRAM-LLaMA3.2-3B-RewardModel

Quantized

(3)

this model