Instructions to use InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT with Transformers:

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

pipe = pipeline("text-generation", model="InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT")
model = AutoModelForMultimodalLM.from_pretrained("InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT

SGLang

How to use InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT 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 "InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT 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 InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT 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 InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT",
    max_seq_length=2048,
)

Docker Model Runner
How to use InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT with Docker Model Runner:
```
docker model run hf.co/InferenceIllusionist/Mistral-RealworldQA-v0.2-7b-SFT
```

Mistral-RealworldQA-v0.2-7b SFT

GGUFs can be found here

An experiment with the goal of reducing hallucinations in VQA

First in a series of experiments centering around fine-tuning for image captioning.

Release Notes

v0.1 - Initial Release
v0.2 (Current)- Updating base model to official Mistral-7b fp16 release, refinements to dataset and instruction formating

Background & Methodology

Mistral-7b-02 base model was fine-tuned using the RealWorldQA dataset, originally provided by the X.Ai Team here: https://x.ai/blog/grok-1.5v

Vision Results

Example 1 Example 2

Experiment yielded model that provides shorter, less verbose output for questions about pictures
The likelihood of hallucinations in output has decreased, however, the model can still be easily influenced to be inaccurate by the user
Best suited for captioning use cases that require concise descriptions and low token counts
This model lacks the conversational prose of Excalibur-7b-DPO and is much "drier" in tone

Requires additional mmproj file. You have two options for vision functionality (available inside this repo):

Select the gguf file of your choice in Koboldcpp as usual, then make sure to choose the mmproj file above in the LLaVA mmproj field of the model submenu: