# McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp

This model is a recipe for converting decoder only language models into text encoders, and it does so with bidirectional attention as one of three steps. The other steps are masked next token prediction and unsupervised contrastive learning, and the source says it can be further fine tuned.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp
- Citation: McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp (retrieved 2026-11-18).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: Vision
- Task: sentence-similarity
- Framework: transformers
- License: mit: Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/MIT.html)
- Source: https://huggingface.co/McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp
- Hosting: hosted (8 files)
- Files: 8 hosted of 11 listed
- Needs its own code to run: Uses custom model code (modeling_mistral_encoder.py). Plain llama.cpp, Ollama and LM Studio commands are not offered for this model unless a GGUF file is listed.
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 8 hosted of 11 listed
- Full repo upstream: unknown
- Download: https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/download-plan)
- Per-file SHA-256: available for 8 of 8 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/files?limit=100
- Availability: Ready
- Downloadable: yes
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 12798
- Stars: 12
- Card completeness: 88%

## Description

This model is a recipe for converting decoder only language models into text encoders, and it does so with bidirectional attention as one of three steps. The other steps are masked next token prediction and unsupervised contrastive learning, and the source says it can be further fine tuned.

## Model Card Facts

- Declared license: mit
- Pipeline: sentence-similarity
- Library: transformers
- Task categories: sentence-similarity

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: thin
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-06-30T02:00:05.806Z.
- Open license detected as mit.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-mcgill-nlp-llm2vec-mistral-7b-instruct-v2-mntp/decentralized-fallbacks
