LLM2Vec Sheared Llama Mntp Supervised measured on 6 of 194 Embeddings benchmarks6
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
86.2MTEB English v2
Apr 2024released
33K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
sBetterAll Mpnet Base v2unstatedOpen+4%—$0.005Max input: 33K tokens → 0K tokensIOpenYuan Embedding 2.0 Enunstated+15%——
BetterQwen 3 Embedding 8BunstatedOpen+11%—$0.01Languages: not verified+1iBetterMultilingual E5 Large InstructunstatedOpen+5%—$0.01Max input: 33K tokens → 1K tokensBetterQwen 3 Embedding 4BunstatedOpen+10%—$0.02Languages: not verified+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
sAll Mpnet Base v2unstatedOpen+4%—$0.005Max input: 33K tokens → 0K tokensQwen 3 Embedding 8BunstatedOpen+11%—$0.01Languages: not verified+1iMultilingual E5 Large InstructunstatedOpen+5%—$0.01Max input: 33K tokens → 1K tokensQwen 3 Embedding 4BunstatedOpen+10%—$0.02Languages: not verified+1
Jina Embeddings v5 Text NanounstatedOpen+6%—$0.02Max input: 33K tokens → 8K tokens+1ModelScoreCostPriceWhat changes
IYuan Embedding 2.0 EnunstatedOpen+15%——KQZhou EmbeddingunstatedOpen+12%——Memory (4-bit): 0.8 GB → 4.2 GBQwen 3 Embedding 8BunstatedOpen+11%—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen+10%—$0.02Languages: not verified+1iJasper Token Compression 600MunstatedOpen+9%——ModelScoreCostPriceWhat changes
MLLM2Vec Meta Llama 3 8B Instruct Mntp SupervisedunstatedOpen+6%——Max input: 33K tokens → 8K tokens+1MLLM2Vec Mistral 7B Instruct v2 Mntp SupervisedunstatedOpen+3%——Memory (4-bit): 0.8 GB → 4.3 GBMLLM2Vec Mistral 7B Instruct v2 Mntp Unsup SimcseunstatedOpen-5%——Memory (4-bit): 0.8 GB → 4.3 GBMLLM2Vec Meta Llama 3 8B Instruct Mntp Unsup SimcseunstatedOpen-6%——Max input: 33K tokens → 8K tokens+1MLLM2Vec Llama 2 7B Chat Hf Mntp Unsup SimcseunstatedOpen-7%——Memory (4-bit): 0.8 GB → 4 GBMLLM2Vec Sheared Llama Mntp Unsup SimcseunstatedOpen-11%——MLLM2Vec Llama 2 7B Chat Hf Mntp SupervisedunstatedOpenn/a——Memory (4-bit): 0.8 GB → 4 GBAll McGill-NLP models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
Benchmarks
in Embeddings & RetrievalBEIR · Retrieval · English51.4#88
FAQ
How much does LLM2Vec Sheared Llama Mntp Supervised cost?›
There is no per-unit API price: self-host only.
Is LLM2Vec Sheared Llama Mntp Supervised free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is LLM2Vec Sheared Llama Mntp Supervised, and what is it best at?›
#50 of 238 in Embeddings.
Is LLM2Vec Sheared Llama Mntp Supervised better than Miniac Embed?›
On MTEB English v2 · Reranking · English, LLM2Vec Sheared Llama Mntp Supervised scores 46.3 vs 46.4 — about the same.
When was LLM2Vec Sheared Llama Mntp Supervised released? Is there a newer version?›
Released 2024-04-09. It is the current version in its line.
Is LLM2Vec Sheared Llama Mntp Supervised open source?›
Yes, the weights are open (MIT licence).
Can I run LLM2Vec Sheared Llama Mntp Supervised locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is LLM2Vec Sheared Llama Mntp Supervised?›
LLM2Vec Sheared Llama Mntp Supervised is an open-weights embeddings & retrieval model from McGill-NLP, released Apr 2024.
What are the best alternatives to LLM2Vec Sheared Llama Mntp Supervised?›
All Mpnet Base v2 (better), Yuan Embedding 2.0 En (open weights).