Instructions to use ecorbari/Gemma-2b-it-Psych-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ecorbari/Gemma-2b-it-Psych-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ecorbari/Gemma-2b-it-Psych-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ecorbari/Gemma-2b-it-Psych-GGUF", dtype="auto")

llama-cpp-python

How to use ecorbari/Gemma-2b-it-Psych-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ecorbari/Gemma-2b-it-Psych-GGUF",
	filename="gemma-2b-it-psych-q5_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ecorbari/Gemma-2b-it-Psych-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf ecorbari/Gemma-2b-it-Psych-GGUF:Q5_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 ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf ecorbari/Gemma-2b-it-Psych-GGUF:Q5_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 ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M

Use Docker

docker model run hf.co/ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M

LM Studio
Jan

vLLM

How to use ecorbari/Gemma-2b-it-Psych-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ecorbari/Gemma-2b-it-Psych-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ecorbari/Gemma-2b-it-Psych-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M

SGLang

How to use ecorbari/Gemma-2b-it-Psych-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ecorbari/Gemma-2b-it-Psych-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ecorbari/Gemma-2b-it-Psych-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ecorbari/Gemma-2b-it-Psych-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ecorbari/Gemma-2b-it-Psych-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ecorbari/Gemma-2b-it-Psych-GGUF with Ollama:
```
ollama run hf.co/ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M
```

Unsloth Studio

How to use ecorbari/Gemma-2b-it-Psych-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 ecorbari/Gemma-2b-it-Psych-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 ecorbari/Gemma-2b-it-Psych-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ecorbari/Gemma-2b-it-Psych-GGUF to start chatting

Docker Model Runner
How to use ecorbari/Gemma-2b-it-Psych-GGUF with Docker Model Runner:
```
docker model run hf.co/ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M
```

Lemonade

How to use ecorbari/Gemma-2b-it-Psych-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ecorbari/Gemma-2b-it-Psych-GGUF:Q5_K_M

Run and chat with the model

lemonade run user.Gemma-2b-it-Psych-GGUF-Q5_K_M

List all available models

lemonade list

Model Card for Gemma-2b-it-Psych-GGUF

Model Summary

Gemma-2b-it-Psych-GGUF is the quantized version of the Gemma-2b-it-Psych-Merged model. It was converted using the llama.cpp pipeline to provide high-performance, low-latency inference on local hardware such as CPUs, consumer GPUs, and mobile devices.

The model is optimized for psychologically safe, empathetic, and supportive interactions, maintaining the fine-tuned alignment of the original model while significantly reducing memory requirements.

Model Details

Key Information

Author: Ederson Corbari (e@NeuroQuest.ai)
Date: February 01, 2026
Base Merged Model: ecorbari/Gemma-2b-it-Psych-Merged
Format: GGUF
Quantization Method: Q5_K_M (Recommended for balancing quality and size)
Release Date: February 01, 2026

File Specifications

File Name	Size	Description
`gemma-2b-it-psych-f16.gguf`	~4.7 GB	High-fidelity FP16 base GGUF
`gemma-2b-it-psych-q5_k_m.gguf`	~1.8 GB	Balanced Q5_K_M quantization (Recommended)

Usage

This model is compatible with any runtime supporting the GGUF format, including llama.cpp, Ollama, Jan, LM Studio, and Text Generation WebUI.

Using with llama.cpp (CLI)

To run a single prompt:

./llama-cli \
  -m gemma-2b-it-psych-q5_k_m.gguf \
  -p "I feel anxious and overwhelmed lately. What should I do?" \
  -n 256 \
  --temp 0.7

To start an interactive chat session:

./llama-cli -m gemma-2b-it-psych-q5_k_m.gguf -cnv

Local Deployment Tools

Jan: Supported as a local model (GGUF/llama.cpp backend).
Ollama: Can be imported using a Modelfile.
LM Studio: Search for the GGUF file or load manually from disk.

Quantization Pipeline

The model followed a strict three-step conversion process:

Merging: The LoRA adapter was merged with the base gemma-2b-it model to create a full FP16 checkpoint.
Conversion: The Hugging Face checkpoint was converted to GGUF format using convert_hf_to_gguf.py.
Quantization: Applied the Q5_K_M method to reduce the model size from 4.7 GB to 1.8 GB while preserving instruction-following accuracy.

Bias, Risks, and Limitations

Medical Disclaimer: This is an experimental model for research and educational purposes. It is not a licensed medical tool and should not be used for clinical diagnosis.
Quantization Loss: While Q5_K_M minimizes performance degradation, some nuances in empathetic tone might differ slightly from the original FP16 model.
Scope: Intended for simulating supportive conversations and studying alignment in the psychological domain.

Technical Maintenance

This model was generated and uploaded using the llama.cpp toolkit and the Hugging Face CLI. For the full conversion scripts and training logs, visit the official GitHub repository.

Downloads last month: 14

GGUF

Model size

3B params

Architecture

gemma

Hardware compatibility

5-bit

Model tree for ecorbari/Gemma-2b-it-Psych-GGUF

Base model

google/gemma-2b-it

Finetuned

ecorbari/Gemma-2b-it-Psych-Merged

Quantized

(1)

this model

ecorbari
/

Gemma-2b-it-Psych-GGUF