jina-v5-text-nano β€” E8 Snap Head (1024-dim)

E8 lattice projection head trained on top of a frozen jinaai/jina-embeddings-v5-text-nano backbone. The head expands 768-dim float embeddings to 1024-dim E8 lattice coordinates β€” enabling O(1) semantic lookup in LatticeMemory.

MTEB STS Results

Task Float baseline E8 Snap Head Delta
STSBenchmark 0.9445 0.9185 -0.0260
STS13 0.8948 0.8711 -0.0237
SICK-R 0.9197 0.8952 -0.0245
STS17 0.8835 0.8604 -0.0231
STS16 0.8687 0.8500 -0.0187
STS15 0.9281 0.9153 -0.0128
STS12 0.8534 0.8408 -0.0126
BIOSSES 0.8744 0.8619 -0.0125
STS22 0.7030 0.6965 -0.0065
STS14 0.8891 0.8929 +0.0038
10-task mean 0.8759 0.8602 -0.0157

STSBenchmark 0.9185 places this model top 10 globally on the MTEB STS leaderboard (260 submitted models as of 2026-06-04).

What This Is

The backbone is fully frozen. The head learns to map 768-dim encoder output onto the nearest E8 lattice point in 1024 dimensions, preserving cosine similarity while producing addresses that can be indexed in an integer hash table.

  • Architecture: OutputOnlyE8Head(input_dim=768, output_dim=1024, hidden_dim=1024)
  • Training: STS-B train/val pairs, 5 epochs, AdamW lr=2e-4, batch 16
  • Inference: frozen jina backbone β†’ E8 head β†’ L2-normalised 1024-dim output

Usage

from sentence_transformers import SentenceTransformer
from liora_core.embed.small_model_e8_head import load_head_checkpoint
from huggingface_hub import snapshot_download

head_dir = snapshot_download("dfrokido/jina-v5-text-nano-e8-snap-1024")
head, _ = load_head_checkpoint(head_dir)

backbone = SentenceTransformer(
    "jinaai/jina-embeddings-v5-text-nano",
    trust_remote_code=True,
    model_kwargs={"default_task": "text-matching"},
)

import torch
texts = ["semantic search", "vector retrieval"]
with torch.no_grad():
    embs = backbone.encode(texts, convert_to_tensor=True, task="text-matching")
    e8_embs = head(embs, snap=True)   # (N, 1024) E8-snapped

Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for dfrokido/jina-v5-text-nano-e8-snap-1024

Adapter
(2)
this model