Instructions to use prithivMLmods/FaithEyes-7B-SFT-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/FaithEyes-7B-SFT-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/FaithEyes-7B-SFT-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/FaithEyes-7B-SFT-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/FaithEyes-7B-SFT-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/FaithEyes-7B-SFT-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/FaithEyes-7B-SFT-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/FaithEyes-7B-SFT-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/FaithEyes-7B-SFT-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/FaithEyes-7B-SFT-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/FaithEyes-7B-SFT-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": "prithivMLmods/FaithEyes-7B-SFT-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/FaithEyes-7B-SFT-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 "prithivMLmods/FaithEyes-7B-SFT-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": "prithivMLmods/FaithEyes-7B-SFT-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "prithivMLmods/FaithEyes-7B-SFT-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": "prithivMLmods/FaithEyes-7B-SFT-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/FaithEyes-7B-SFT-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use prithivMLmods/FaithEyes-7B-SFT-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/FaithEyes-7B-SFT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/FaithEyes-7B-SFT-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.FaithEyes-7B-SFT-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

FaithEyes-7B-SFT-GGUF

FaithEyes-7B-SFT is a supervised fine-tuned vision-language model built on Qwen2.5-VL-7B-Instruct, serving as the cold-start first stage of the two-stage FaithEyes framework (SFT + RL), which introduces a multi-agent self-judging paradigm where a single VLM simultaneously acts as a main agent — solving visual questions through interleaved reasoning and executable Python-based tool calls (cropping, zooming, rotation, contrast adjustment, arithmetic) — and a subagent that evaluates whether each process image generated by the main agent is genuinely helpful for answering the question, emitting a structured JSON verdict {"is_helpful": true/false, "reasons": ...} that is injected back into the tool observation to steer subsequent reasoning and scale tool rewards via a helpful-tool ratio to suppress reward hacking. Through this SFT stage, the model acquires three core capabilities: code-based tool use, faithfulness judging, and feedback-driven reasoning, though as noted by the authors, this checkpoint primarily imitates demonstrations rather than autonomously discriminating helpful from unhelpful tool calls — a capability that is further developed in the subsequent RL checkpoint. FaithEyes-7B-SFT on Hugging Face

Model Files

File Name	Quant Type	File Size	File Link	Description
FaithEyes-7B-SFT.BF16.gguf	BF16	15.2 GB	Link	Full BF16 weights. Highest quality, largest file size.
FaithEyes-7B-SFT.Q3_K_L.gguf	Q3_K_L	4.09 GB	Link	Lower quality but usable, good for low RAM availability.
FaithEyes-7B-SFT.Q3_K_M.gguf	Q3_K_M	3.81 GB	Link	Low quality.
FaithEyes-7B-SFT.Q4_K_M.gguf	Q4_K_M	4.68 GB	Link	Good quality, default size for most use cases, recommended.
FaithEyes-7B-SFT.Q4_K_S.gguf	Q4_K_S	4.46 GB	Link	Slightly lower quality with more space savings, recommended.
FaithEyes-7B-SFT.Q5_K_M.gguf	Q5_K_M	5.44 GB	Link	High quality, recommended.
FaithEyes-7B-SFT.Q5_K_S.gguf	Q5_K_S	5.32 GB	Link	High quality, recommended.
FaithEyes-7B-SFT.mmproj-bf16.gguf	mmproj-bf16	1.36 GB	Link	Multimodal projection file in BF16 format. Used for vision/language models.