Image-Text-to-Text
Transformers.js
ONNX
English
llava
text-generation
multimodal
qwen
conversational
Instructions to use onnx-community/nanoLLaVA-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/nanoLLaVA-1.5 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-text-to-text', 'onnx-community/nanoLLaVA-1.5');
Download config.json from onnx-community/nanoLLaVA-1.5: direct link, hf CLI and curl.
- Browser
- Download file 2.18 kB
-
https://huggingface.co/onnx-community/nanoLLaVA-1.5/resolve/main/config.json
- Command line
-
hf download hf://onnx-community/nanoLLaVA-1.5/config.json
-
curl -L -o config.json https://huggingface.co/onnx-community/nanoLLaVA-1.5/resolve/main/config.json
2.18 kB
| { | |
| "_name_or_path": "qnguyen3/nanoLLaVA-1.5", | |
| "architectures": [ | |
| "BunnyQwenForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151645, | |
| "eos_token_id": 151645, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "image_aspect_ratio": "pad", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2816, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 21, | |
| "mm_hidden_size": 1152, | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_vision_tower": "google/siglip-so400m-patch14-384", | |
| "language_model": "vilm/Quyen-SE-v0.1", | |
| "model_type": "llava", | |
| "text_config": { | |
| "_name_or_path": "vilm/Quyen-SE-v0.1", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2816, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 21, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_image_tokens": 729, | |
| "num_key_value_heads": 16, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.38.1", | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "vision_config": { | |
| "hidden_size": 1152, | |
| "image_size": 384, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 729, | |
| "patch_size": 14 | |
| }, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_image_tokens": 729, | |
| "num_key_value_heads": 16, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "tokenizer_model_max_length": 4096, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.39.2", | |
| "tune_mm_mlp_adapter": false, | |
| "use_cache": false, | |
| "use_mm_proj": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936, | |
| "image_token_index": -200 | |
| } |