Text Generation
Transformers
Safetensors
PyTorch
English
modernbert
fill-mask
text-diffusion
discrete-diffusion
mdlm
seed-diffusion
generative-ai
conversational
Instructions to use JorgeVanco/diffusionGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JorgeVanco/diffusionGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JorgeVanco/diffusionGPT") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("JorgeVanco/diffusionGPT") model = AutoModelForMaskedLM.from_pretrained("JorgeVanco/diffusionGPT") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use JorgeVanco/diffusionGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JorgeVanco/diffusionGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JorgeVanco/diffusionGPT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/JorgeVanco/diffusionGPT
- SGLang
How to use JorgeVanco/diffusionGPT 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 "JorgeVanco/diffusionGPT" \ --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": "JorgeVanco/diffusionGPT", "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 "JorgeVanco/diffusionGPT" \ --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": "JorgeVanco/diffusionGPT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use JorgeVanco/diffusionGPT with Docker Model Runner:
docker model run hf.co/JorgeVanco/diffusionGPT
| { | |
| "architectures": [ | |
| "ModernBertForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 50256, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 50281, | |
| "custom_pipelines": { | |
| "text-diffusion": { | |
| "impl": "pipeline.TextDiffusionPipeline", | |
| "pt": [ | |
| "AutoModelForMaskedLM" | |
| ], | |
| "tf": [] | |
| } | |
| }, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "dtype": "float32", | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 50259, | |
| "global_attn_every_n_layers": 3, | |
| "global_rope_theta": 160000.0, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 1280, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "layer_norm_eps": 1e-05, | |
| "local_attention": 128, | |
| "local_rope_theta": 10000.0, | |
| "mask_token_id": 50258, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 10, | |
| "num_hidden_layers": 20, | |
| "pad_token_id": 50257, | |
| "position_embedding_type": "absolute", | |
| "repad_logits_with_grad": false, | |
| "sep_token_id": 50282, | |
| "seq_length": 2048, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "transformers_version": "4.56.2", | |
| "use_cache": false, | |
| "vocab_size": 50263 | |
| } | |