LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse measured on 6 of 261 Embeddings benchmarks6
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
77.9MTEB English v2
Apr 2024released
33K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen+12%—$0.002Max input: 33K tokens → 2K tokens+1KOpenQZhou Embeddingunstated+19%——Memory (4-bit): 4 GB → 4.2 GB
BetterBge Base En v1.5unstatedOpen+11%—$0.005Max input: 33K tokens → 1K tokensiBetterE5 Base v2unstatedOpen+10%—$0.005Max input: 33K tokens → 1K tokenstBetterGte BaseunstatedOpen+9%—$0.005Max input: 33K tokens → 1K tokensModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+12%—$0.002Max input: 33K tokens → 2K tokens+1Bge Base En v1.5unstatedOpen+11%—$0.005Max input: 33K tokens → 1K tokensiE5 Base v2unstatedOpen+10%—$0.005Max input: 33K tokens → 1K tokenstGte BaseunstatedOpen+9%—$0.005Max input: 33K tokens → 1K tokenssAll Mpnet Base v2unstatedOpen+7%—$0.005Max input: 33K tokens → 0K tokensModelScoreCostPriceWhat changes
KQZhou EmbeddingunstatedOpen+19%——Memory (4-bit): 4 GB → 4.2 GBiJasper Token Compression 600MunstatedOpen+16%——KNano Em1 0.6B v2.1unstatedOpen+15%——Max input: 33K tokens → 8K tokens
NV Embed v2unstatedOpen+14%——Memory (4-bit): 4 GB → 4.7 GBaLGAI Embedding PreviewunstatedOpen+14%——Memory (4-bit): 4 GB → 4.3 GBModelScoreCostPriceWhat changes
MLLM2Vec Llama 2 7B Chat Hf Mntp SupervisedunstatedOpen+13%——MLLM2Vec Mistral 7B Instruct v2 Mntp SupervisedunstatedOpen+13%——Memory (4-bit): 4 GB → 4.3 GBMLLM2Vec Meta Llama 3 8B Instruct Mntp SupervisedunstatedOpen+13%——Max input: 33K tokens → 8K tokens+1MLLM2Vec Sheared Llama Mntp SupervisedunstatedOpen+11%——MLLM2Vec Mistral 7B Instruct v2 Mntp Unsup SimcseunstatedOpen+4%——Memory (4-bit): 4 GB → 4.3 GBMLLM2Vec Meta Llama 3 8B Instruct Mntp Unsup SimcseunstatedOpensame——Max input: 33K tokens → 8K tokens+1MLLM2Vec Sheared Llama Mntp Unsup SimcseunstatedOpen-7%——All McGill-NLP models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 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 · Mean over tasks · English36.7#155
BEIR · Retrieval · English36.7#155
FAQ
How much does LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse cost?›
There is no per-unit API price: self-host only.
Is LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse, and what is it best at?›
#203 of 238 in Embeddings.
Is LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse better than LLM2Vec Meta Llama 3 8B Instruct Mntp Unsup Simcse?›
On MTEB English v2 · Pair Classification · English, LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse scores 77.9 vs 78 — about the same.
When was LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse released? Is there a newer version?›
Released 2024-04-09. It is the current version in its line.
Is LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse open source?›
Yes, the weights are open (MIT licence).
Can I run LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse?›
LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse is an open-weights embeddings & retrieval model from McGill-NLP, released Apr 2024.
What are the best alternatives to LLM2Vec Llama 2 7B Chat Hf Mntp Unsup Simcse?›
EmbeddingGemma 300M (better), QZhou Embedding (open weights).