GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Jgmorenof
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Jgmorenof
Model Tree
Qwen/Qwen3-Embedding-8B
Input Modalities
Output Modalities
Supported Functionality
20,000 training pairs (a random subset); symmetric in-batch contrastive loss (InfoNCE in both directions) with gradient caching, batch 128, 1 epoch, learning rate 0.0001, maximum input length 512 tokens, LoRA rank 16, seed 13. Films of SemEval-2026 Task 4 and TREC ToT 2023 (train and dev targets) are excluded from training.
NS: accuracy on the 355 leak-free SemEval-2026 Task 4 track-B test triples. PLOTS-IR: nDCG@10 on the test queries (M: entity-masked). ToT: TREC ToT 2023 dev queries.
| NS acc. | Full | Full M | First | Last | Last M | ToT nDCG@10 | ToT R@100 | |
|---|---|---|---|---|---|---|---|---|
| this model | 0.670 | 0.996 | 0.947 | 0.876 | 0.528 | 0.176 | 0.333 | 0.660 |
| Qwen3-Embedding-8B, zero-shot | 0.642 | 0.991 | 0.912 | 0.848 | 0.512 | 0.183 | 0.241 | 0.580 |
python
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Qwen/Qwen3-Embedding-8B", trust_remote_code=True)model.load_adapter("Jgmorenof/plots-qwen3-embedding-8b-lora")queries = ["<plot summary or description of a film, in any language>"]documents = ["<English plot summary>"]q = model.encode(queries, prompt="Instruct: Given a story summary, retrieve the plot summary of the same film\nQuery:")D = model.encode(documents, prompt="")scores = model.similarity(q, D)peft.The weights keep the license of the base model (apache-2.0). The training data (PLOTS) is CC BY-SA 4.0.
bibtex
@misc{moreno2026plots, title = {{PLOTS} -- Same Story, Different Words: Paired Plot Outlines for Narrative Similarity and Retrieval}, author = {Moreno, Jose G. and Hamdi, Ahmed and Boros, Emanuela and Jatowt, Adam and Bordea, Georgeta and Gonz{\'a}lez-Gallardo, Carlos-Emiliano and Doucet, Antoine}, year = {2026}, howpublished = {\url{https://huggingface.co/datasets/Jgmorenof/PLOTS}}}from sentence_transformers import SentenceTransformer model = SentenceTransformer("Qwen/Qwen3-Embedding-8B", trust_remote_code=True)model.load_adapter("Jgmorenof/plots-qwen3-embedding-8b-lora")queries = ["<plot summary or description of a film, in any language>"]documents = ["<English plot summary>"]q = model.encode(queries, prompt="Instruct: Given a story summary, retrieve the plot summary of the same film\nQuery:")D = model.encode(documents, prompt="")scores = model.similarity(q, D)@misc{moreno2026plots, title = {{PLOTS} -- Same Story, Different Words: Paired Plot Outlines for Narrative Similarity and Retrieval}, author = {Moreno, Jose G. and Hamdi, Ahmed and Boros, Emanuela and Jatowt, Adam and Bordea, Georgeta and Gonz{\'a}lez-Gallardo, Carlos-Emiliano and Doucet, Antoine}, year = {2026}, howpublished = {\url{https://huggingface.co/datasets/Jgmorenof/PLOTS}}}