Image-Text-to-Text
Transformers
PyTorch
multilingual
internvl_chat
feature-extraction
internvl
custom_code
Instructions to use OpenGVLab/InternVL-Chat-V1-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/InternVL-Chat-V1-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL-Chat-V1-1", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenGVLab/InternVL-Chat-V1-1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use OpenGVLab/InternVL-Chat-V1-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenGVLab/InternVL-Chat-V1-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenGVLab/InternVL-Chat-V1-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OpenGVLab/InternVL-Chat-V1-1
- SGLang
How to use OpenGVLab/InternVL-Chat-V1-1 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 "OpenGVLab/InternVL-Chat-V1-1" \ --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": "OpenGVLab/InternVL-Chat-V1-1", "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 "OpenGVLab/InternVL-Chat-V1-1" \ --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": "OpenGVLab/InternVL-Chat-V1-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use OpenGVLab/InternVL-Chat-V1-1 with Docker Model Runner:
docker model run hf.co/OpenGVLab/InternVL-Chat-V1-1
| { | |
| "_commit_hash": null, | |
| "architectures": [ | |
| "InternVLChatModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", | |
| "AutoModel": "modeling_internvl_chat.InternVLChatModel", | |
| "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel" | |
| }, | |
| "system_message": "", | |
| "downsample_ratio": 0.5, | |
| "dynamic_image_size": false, | |
| "force_image_size": 448, | |
| "llm_config": { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 1, | |
| "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": 2, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 4096, | |
| "min_length": 0, | |
| "model_type": "llama", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 40, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "pretraining_tp": 1, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 3.0, | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 10000.0, | |
| "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": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "bfloat16", | |
| "torchscript": false, | |
| "transformers_version": "4.32.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": true, | |
| "use_cache": true, | |
| "vocab_size": 41919 | |
| }, | |
| "max_dynamic_patch": 1, | |
| "min_dynamic_patch": 1, | |
| "model_type": "internvl_chat", | |
| "ps_version": "v1", | |
| "select_layer": -4, | |
| "template": "internvl_zh", | |
| "torch_dtype": "bfloat16", | |
| "use_backbone_lora": 0, | |
| "use_llm_lora": 0, | |
| "use_thumbnail": false, | |
| "vision_config": { | |
| "architectures": [ | |
| "InternVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "drop_path_rate": 0.0, | |
| "dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 3200, | |
| "image_size": 448, | |
| "initializer_factor": 0.1, | |
| "initializer_range": 1e-10, | |
| "intermediate_size": 12800, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "intern_vit_6b", | |
| "norm_type": "rms_norm", | |
| "num_attention_heads": 25, | |
| "num_channels": 3, | |
| "num_hidden_layers": 48, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "patch_size": 14, | |
| "qk_normalization": true, | |
| "qkv_bias": false, | |
| "return_dict": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.32.0", | |
| "use_bfloat16": true, | |
| "use_flash_attn": true | |
| } | |
| } | |