Text Generation
Transformers
Safetensors
English
multi_modality
janus
multimodal
text-to-image
image-to-text
image-to-image
unified-model
Instructions to use kiel2/KielGen-Fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kiel2/KielGen-Fast with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kiel2/KielGen-Fast")# Load model directly from transformers import MultiModalityCausalLM model = MultiModalityCausalLM.from_pretrained("kiel2/KielGen-Fast", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kiel2/KielGen-Fast with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kiel2/KielGen-Fast" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kiel2/KielGen-Fast", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kiel2/KielGen-Fast
- SGLang
How to use kiel2/KielGen-Fast 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 "kiel2/KielGen-Fast" \ --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": "kiel2/KielGen-Fast", "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 "kiel2/KielGen-Fast" \ --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": "kiel2/KielGen-Fast", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kiel2/KielGen-Fast with Docker Model Runner:
docker model run hf.co/kiel2/KielGen-Fast
KielGen-Fast
KielGen-Fast is a fine-tuned multi-modal vision-language model based on the Janus architecture. It unifies three core capabilities within a single autoregressive framework:
- Text Generation: Standard conversational reasoning and open-ended text answers.
- Image Understanding (Image-to-Text): Visual question answering, scene description, and multimodal analysis.
- Text-to-Image Generation: Generating high-fidelity visual assets and creative artwork from descriptive text prompts.
Model Details
- Model Type: Multi-Modal Causal Language Model (
MultiModalityCausalLM) - Base Model:
deepseek-ai/Janus-Pro-7B - Architecture Highlights: Decoupled visual encoder pathways for understanding combined with a vector-quantized token decoding head for native image synthesis.
- Weights Format: Single unified
.safetensorsfile (model.safetensors) designed for optimized cloud deployment and fast loading.
Quick Start: Loading the Model
Load your fine-tuned model and processor directly from Hugging Face using standard transformers:
import torch
from transformers import AutoProcessor, AutoModel
repo_id = "kiel2/KielGen-Fast"
processor = AutoProcessor.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModel.from_pretrained(
repo_id,
trust_remote_code=True,
torch_dtype=torch.bfloat16,
device_map="auto"
)
print("KielGen-Fast loaded successfully!")
- Downloads last month
- 9
Model tree for kiel2/KielGen-Fast
Base model
deepseek-ai/Janus-Pro-7B