Sentence Similarity
sentence-transformers
Safetensors
Transformers
English
Chinese
qwen2_vl
image-text-to-text
mteb
Qwen2-VL
vidore
custom_code
Eval Results (legacy)
Instructions to use Alibaba-NLP/gme-Qwen2-VL-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Alibaba-NLP/gme-Qwen2-VL-7B-Instruct with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Alibaba-NLP/gme-Qwen2-VL-7B-Instruct", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use Alibaba-NLP/gme-Qwen2-VL-7B-Instruct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Alibaba-NLP/gme-Qwen2-VL-7B-Instruct", trust_remote_code=True) model = AutoModelForImageTextToText.from_pretrained("Alibaba-NLP/gme-Qwen2-VL-7B-Instruct", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct", | |
| "architectures": [ | |
| "Qwen2VLForConditionalGeneration", | |
| "GmeQwen2VL" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_gme_qwen2vl.GmeQwen2VLConfig", | |
| "AutoModel": "modeling_gme_qwen2vl.GmeQwen2VL" | |
| }, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2_vl", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_section": [ | |
| 16, | |
| 24, | |
| 24 | |
| ], | |
| "type": "mrope" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.45.0.dev0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "in_chans": 3, | |
| "model_type": "qwen2_vl", | |
| "spatial_patch_size": 14 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vision_token_id": 151654, | |
| "vocab_size": 152064 | |
| } | |