Feature Extraction
sentence-transformers
Safetensors
GGUF
English
Chinese
multilingual
qwen3_5
multimodal
embeddings
retrieval
quantization
mixed-precision
w4a8
fp8
int4
svd
mrl
text-embeddings
image-embedding
video-embedding
cross-modal
custom_code
Eval Results (legacy)
Instructions to use ewin-reg/WeMM-Embedding-2B-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use ewin-reg/WeMM-Embedding-2B-Quantized with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("ewin-reg/WeMM-Embedding-2B-Quantized", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Qwen3_5ForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_token_id": 248056, | |
| "model_type": "qwen3_5", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 16, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_text", | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "vocab_size": 248078 | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.2.0", | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [], | |
| "depth": 24, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1024, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "model_type": "qwen3_5", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 2048, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053, | |
| "auto_map": { | |
| "AutoModel": "modeling_wemm_embedding.WeMMEmbedding", | |
| "AutoModelForCausalLM": "modeling_wemm_embedding.WeMMEmbedding" | |
| }, | |
| "matryoshka_dimensions": [ | |
| 64, | |
| 128, | |
| 256, | |
| 512, | |
| 1024, | |
| 2048 | |
| ] | |
| } |