Model reference · open weights

LLM2Vec-Meta-Llama-3-mntp-supervised

LLM2Vec-Meta-Llama-3-mntp-supervised is an open-weight embedding model from McGill-NLP, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings McGill-NLP 1 variants 96k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What LLM2Vec-Meta-Llama-3-mntp-supervised is

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders LLM2Vec is a simple recipe to convert decoder-only LLMs into text encoders. It consists of 3 simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. The model can be further fine-tuned to achieve state-of-the-art performance. - Repository: https://github.com/McGill-NLP/llm2vec - Paper: https://arxiv.org/abs/2404.05961 Installation Usage Questions If you have any question about the code, feel free to email Parishad (parishad.behnamghader@mila.quebec) and Vaibhav (vaibhav.adlakha@mila.quebec).

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerMcGill-NLP
TypeEmbedding models
Variants1
Runs withpeft
Released2024-04-30
Popularity96k downloads / month
Likes53
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervisedBF16Weights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
ClassificationMTEB AmazonCounterfactualClassification (en)accuracy79.94
ClassificationMTEB AmazonCounterfactualClassification (en)ap44.932
ClassificationMTEB AmazonCounterfactualClassification (en)f174.303
ClassificationMTEB AmazonPolarityClassificationaccuracy86.067
ClassificationMTEB AmazonPolarityClassificationap81.971
ClassificationMTEB AmazonPolarityClassificationf186.006
ClassificationMTEB AmazonReviewsClassification (en)accuracy46.836
ClassificationMTEB AmazonReviewsClassification (en)f146.051
RetrievalMTEB ArguAnamap_at_137.98
RetrievalMTEB ArguAnamap_at_1054.167
RetrievalMTEB ArguAnamap_at_10054.735
RetrievalMTEB ArguAnamap_at_100054.738
RetrievalMTEB ArguAnamap_at_349.384
RetrievalMTEB ArguAnamap_at_552.285
RetrievalMTEB ArguAnamrr_at_138.549
RetrievalMTEB ArguAnamrr_at_1054.351
RetrievalMTEB ArguAnamrr_at_10054.932
RetrievalMTEB ArguAnamrr_at_100054.935
RetrievalMTEB ArguAnamrr_at_349.585
RetrievalMTEB ArguAnamrr_at_552.469
RetrievalMTEB ArguAnandcg_at_137.98
RetrievalMTEB ArguAnandcg_at_1062.779
RetrievalMTEB ArguAnandcg_at_10064.986
RetrievalMTEB ArguAnandcg_at_100065.036

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys llm2vec-meta-llama-3-mntp-supervised for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (llm2vec-meta-llama-3-mntp-supervised below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"llm2vec-meta-llama-3-mntp-supervised","input":"text to embed"}'

Details

Languages, data & research

Languages

en

Tags

peft safetensors text-embedding embeddings information-retrieval beir text-classification language-model text-clustering text-semantic-similarity text-evaluation text-reranking feature-extraction sentence-similarity

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want LLM2Vec-Meta-Llama-3-mntp-supervised on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms