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
Commit History
29 days ago
-
card: mark the image and video fidelity rows as unreproducible, point at the user's re-measurement
Verified signature524bbe6
-
Add notes on Apple Silicon, MPS support and the tied lm_head
Verified signatureabed8fd
-
fix: no-op tie_weights for transformers 5.x compatibility
Verified signaturea783528 -
fix(mps): route F.embedding for Metal shader interlock and add load-time MPS dequant fallback
Verified signature61611a4
-
docs: refactor architecture section into clean headers with standalone KaTeX display math
Verified signature9b76bbf -
docs: fix broken multi-line LaTeX block swallowing list text
Verified signature83b247b -
docs: simplify inline LaTeX notation and adjust vocab savings
Verified signature70c93f5 -
docs: clean markdown formatting, fix tables and simplify LaTeX math
Verified signatureb43c019
-
docs: publish verified sub-1% degradation empirical benchmarks (0.7796% degradation, 99.2204% fidelity)
Verified signature5f7885a
-
docs: update empirical benchmark scoreboard with verified v18 production numbers
Verified signaturedc60b2b -
docs: update empirical benchmarks (99.22% fidelity, 0.78% degradation, 1.75GB disk size)
Verified signature8151f7b -
feat: Final Hybrid FP8 + INT4-g16 (99.2204% fidelity, 0.7796% degradation, 1.75GB)
Verified signaturebe2b119 -
feat: tie_word_embeddings=True for pure embedding model
Verified signatured0c1550 -
feat: remote code support for Hybrid FP8 Attn/GDN + INT4-g16 MLP
Verified signature6f3907c -
feat: Hybrid FP8 + INT4-g16 (99.2204% fidelity, 0.7796% degradation, 2.04GB)
Verified signature76a1447 -
feat: support FP8RowScaledEmbedding and W4A8 Group-32 linear in remote code
Verified signature246da84 -
feat: FP8 Row-Scaled Embeddings + W4A8-G32 Linear (97.3419% fidelity, 2.6581% degradation, 1.73GB)
Verified signature64f07d2 -
docs: sanitize KaTeX syntax ($...$ delims, \geq, and variable formatting)
Verified signaturef6702a4 -
docs: clarify GGUF modality comparison labels to Not Supported (Text-Only)
Verified signaturece5497a -
docs: fix KaTeX equation blocks and sanitize table angle brackets
Verified signature72d5bcb -
docs: publish comprehensive Model Card with 7-format comparisons, architecture deep-dive, MRL, and multimodal inference
Verified signature82f3f6e
-
docs: update empirical milestone metrics for 4-Pillar checkpoint (96.7267% fidelity)
Verified signature28e3c7a -
feat: support SVDLowRankW4A8Embedding and PAS FP8 in remote code
Verified signature081a12d -
feat: 4-Pillar SVD Vocab + PAS FP8 Quantization (96.7267% fidelity, 3.2733% degradation)
Verified signature78f85d3 -
docs: update empirical MRL benchmark metrics and clarify CPU validation
Verified signature1d11835 -
empirical: measured live forward inference (96.5900% fidelity, 3.4100% degradation)
Verified signature257b58f -
fix: align visual pos_embed shape and ensure seamless loadability
Verified signaturecf46424 -
docs: clean unicode multiplication symbols in Model Card
Verified signature4b7d708 -
docs: expand Model Card with architecture deep-dive, MRL benchmarks, layer breakdown, and hardware profiling
Verified signature646bd62 -
docs: fix KaTeX and Markdown table rendering syntax for fidelity and KL divergence
Verified signaturee22486a -
Add comprehensive Model Card and GGUF/NVFP4 comparative evaluation matrix
Verified signaturef1d8e44 -
Release WeMM-Embedding-2B-Quantized: Native Sub-1.3GB SafeTensors with <1.0% degradation
Verified signature6f43aa3 -
initial commit
Verified signatured50030f