Text Generation
Transformers
PyTorch
devil_qwen2
multimodal
video-llm
video-understanding
video-grounding
spatio-temporal-grounding
temporal-grounding
referring-expression-comprehension
grounding
reasoning
custom_code
conversational
Instructions to use gaostar/DeViL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gaostar/DeViL-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="gaostar/DeViL-7B", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("gaostar/DeViL-7B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use gaostar/DeViL-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gaostar/DeViL-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gaostar/DeViL-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/gaostar/DeViL-7B
- SGLang
How to use gaostar/DeViL-7B 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 "gaostar/DeViL-7B" \ --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": "gaostar/DeViL-7B", "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 "gaostar/DeViL-7B" \ --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": "gaostar/DeViL-7B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use gaostar/DeViL-7B with Docker Model Runner:
docker model run hf.co/gaostar/DeViL-7B
| { | |
| "_name_or_path": "weights/gdino_vllama_stage2_no_temporal/llm_lo_merge", | |
| "architectures": [ | |
| "DeViLQwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_devil.DeViLQwen2Config", | |
| "AutoModelForCausalLM": "modeling_devil.DeViLQwen2ForCausalLM" | |
| }, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "g_dino_lr": 0.0001, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_aspect_ratio": "square", | |
| "image_size": -1, | |
| "image_token_index": 151665, | |
| "image_token_length": 1, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "is_alignment": false, | |
| "llm_lr": 1e-05, | |
| "max_frames": 180, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "mm_hidden_size": 1152, | |
| "mm_projector_lr": 1e-05, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_vision_encoder": "weights/VL3-SigLIP-NaViT", | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -1, | |
| "model_type": "devil_qwen2", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "query_end_index": 151670, | |
| "query_start_index": 151669, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tbox_index": 151668, | |
| "tie_word_embeddings": false, | |
| "tokenizer_model_max_length": 16384, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.49.0", | |
| "use_cache": true, | |
| "use_flash_loss": false, | |
| "use_gdino": true, | |
| "use_mm_proj": true, | |
| "use_sliding_window": false, | |
| "use_token_compression": true, | |
| "vision_encoder": "weights/VL3-SigLIP-NaViT", | |
| "vision_encoder_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "intermediate_size": 4304, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-06, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "Devil_vision_encoder", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "vision_encoder_lr": null, | |
| "vocab_size": 152064 | |
| } | |