Skip to content
BranchesTags

Repository files navigation

MTEB Paper resources

This repository contains scripts & resources for the MTEB paper. Some scripts rely on a results folder, which can be obtained via git clone https://huggingface.co/datasets/mteb/results. These scripts are unlikely to work with the latest version of MTEB but rather the 1.0.0 release when the paper was released; they are solely to ease reproduction of the original paper. Please refer to the MTEB repository for scripts and resources to work with the latest version and please open any issues with MTEB there; if you have issues with the original MTEB paper you can open them here.

Talks

Benchmark

Basic with Internet

frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")

No Internet Access (Download data first)

importosos.environ["HF_DATASETS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_CACHE"]="/gpfswork/rech/six/commun/models"os.environ["HF_DATASETS_CACHE"]="/gpfswork/rech/six/commun/datasets"os.environ["HF_MODULES_CACHE"]="/gpfswork/rech/six/commun/modules"os.environ["HF_METRICS_CACHE"]="/gpfswork/rech/six/commun/metrics"frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")

Env Setup

export CONDA_ENVS_PATH=$six_ALL_CCFRWORK/conda
conda create -y -n hf-prod python=3.8
conda activate hf-prod
# pt-1.10.1 / cuda 11.3
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# Custom fork that uses offline datasets!pip install --upgrade git+https://github.com/Muennighoff/mteb.git@offlineaccess
!pip install --upgrade git+https://github.com/Muennighoff/sentence-transformers.git@sgpt_poolings
# If you want to run BEIR tasks!pip install --upgrade git+https://github.com/beir-cellar/beir.git

Model setup

Download

importosimportsentence_transformersos.environ["SENTENCE_TRANSFORMERS_HOME"] ="/gpfswork/rech/six/commun/models"sentence_transformers_cache_dir=os.getenv("SENTENCE_TRANSFORMERS_HOME")
model_repo="sentence-transformers/allenai-specter"revision="29f9f45ff2a85fe9dfe8ce2cef3d8ec4e65c5f37"model_path=os.path.join(sentence_transformers_cache_dir, model_repo.replace("/", "_"))
model_path_tmp=sentence_transformers.util.snapshot_download(
repo_id=model_repo,
revision=revision,
cache_dir=sentence_transformers_cache_dir,
library_name="sentence-transformers",
library_version=sentence_transformers.__version__,
ignore_files=["flax_model.msgpack", "rust_model.ot", "tf_model.h5",],
)
os.rename(model_path_tmp, model_path)

Load

model=SentenceTransformer("/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit")

About

Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark"

Resources

Readme
Activity
Custom properties

Stars

18 stars

Watchers

1 watching

Forks

5 forks
Report repository

Releases

Packages

Contributors

Languages

, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
GitHub - embeddings-benchmark/mtebpaper: Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark" · GitHub
Skip to content
BranchesTags
Repository files navigation
MTEB Paper resources
This repository contains scripts & resources for the MTEB paper. Some scripts rely on a results folder, which can be obtained via git clone https://huggingface.co/datasets/mteb/results. These scripts are unlikely to work with the latest version of MTEB but rather the 1.0.0 release when the paper was released; they are solely to ease reproduction of the original paper. Please refer to the MTEB repository for scripts and resources to work with the latest version and please open any issues with MTEB there; if you have issues with the original MTEB paper you can open them here.
Talks
Benchmark
Basic with Internet
frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
No Internet Access (Download data first)
importosos.environ["HF_DATASETS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_CACHE"]="/gpfswork/rech/six/commun/models"os.environ["HF_DATASETS_CACHE"]="/gpfswork/rech/six/commun/datasets"os.environ["HF_MODULES_CACHE"]="/gpfswork/rech/six/commun/modules"os.environ["HF_METRICS_CACHE"]="/gpfswork/rech/six/commun/metrics"frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
Env Setup
export CONDA_ENVS_PATH=$six_ALL_CCFRWORK/conda
conda create -y -n hf-prod python=3.8
conda activate hf-prod
# pt-1.10.1 / cuda 11.3
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# Custom fork that uses offline datasets!pip install --upgrade git+https://github.com/Muennighoff/mteb.git@offlineaccess
!pip install --upgrade git+https://github.com/Muennighoff/sentence-transformers.git@sgpt_poolings
# If you want to run BEIR tasks!pip install --upgrade git+https://github.com/beir-cellar/beir.git
Model setup
Download
importosimportsentence_transformersos.environ["SENTENCE_TRANSFORMERS_HOME"] ="/gpfswork/rech/six/commun/models"sentence_transformers_cache_dir=os.getenv("SENTENCE_TRANSFORMERS_HOME")
model_repo="sentence-transformers/allenai-specter"revision="29f9f45ff2a85fe9dfe8ce2cef3d8ec4e65c5f37"model_path=os.path.join(sentence_transformers_cache_dir, model_repo.replace("/", "_"))
model_path_tmp=sentence_transformers.util.snapshot_download(
repo_id=model_repo,
revision=revision,
cache_dir=sentence_transformers_cache_dir,
library_name="sentence-transformers",
library_version=sentence_transformers.__version__,
ignore_files=["flax_model.msgpack", "rust_model.ot", "tf_model.h5",],
)
os.rename(model_path_tmp, model_path)
Load
model=SentenceTransformer("/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit")
About
Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark"
Resources
Readme
Activity
Custom properties
Stars
18 stars
Watchers
1 watching
Forks
5 forks
Report repository
Releases
Packages
Contributors
Languages

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
GitHub - embeddings-benchmark/mtebpaper: Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark" · GitHub
Skip to content
BranchesTags
Repository files navigation
MTEB Paper resources
This repository contains scripts & resources for the MTEB paper. Some scripts rely on a results folder, which can be obtained via git clone https://huggingface.co/datasets/mteb/results. These scripts are unlikely to work with the latest version of MTEB but rather the 1.0.0 release when the paper was released; they are solely to ease reproduction of the original paper. Please refer to the MTEB repository for scripts and resources to work with the latest version and please open any issues with MTEB there; if you have issues with the original MTEB paper you can open them here.
Talks
Benchmark
Basic with Internet
frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
No Internet Access (Download data first)
importosos.environ["HF_DATASETS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_CACHE"]="/gpfswork/rech/six/commun/models"os.environ["HF_DATASETS_CACHE"]="/gpfswork/rech/six/commun/datasets"os.environ["HF_MODULES_CACHE"]="/gpfswork/rech/six/commun/modules"os.environ["HF_METRICS_CACHE"]="/gpfswork/rech/six/commun/metrics"frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
Env Setup
export CONDA_ENVS_PATH=$six_ALL_CCFRWORK/conda
conda create -y -n hf-prod python=3.8
conda activate hf-prod
# pt-1.10.1 / cuda 11.3
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# Custom fork that uses offline datasets!pip install --upgrade git+https://github.com/Muennighoff/mteb.git@offlineaccess
!pip install --upgrade git+https://github.com/Muennighoff/sentence-transformers.git@sgpt_poolings
# If you want to run BEIR tasks!pip install --upgrade git+https://github.com/beir-cellar/beir.git
Model setup
Download
importosimportsentence_transformersos.environ["SENTENCE_TRANSFORMERS_HOME"] ="/gpfswork/rech/six/commun/models"sentence_transformers_cache_dir=os.getenv("SENTENCE_TRANSFORMERS_HOME")
model_repo="sentence-transformers/allenai-specter"revision="29f9f45ff2a85fe9dfe8ce2cef3d8ec4e65c5f37"model_path=os.path.join(sentence_transformers_cache_dir, model_repo.replace("/", "_"))
model_path_tmp=sentence_transformers.util.snapshot_download(
repo_id=model_repo,
revision=revision,
cache_dir=sentence_transformers_cache_dir,
library_name="sentence-transformers",
library_version=sentence_transformers.__version__,
ignore_files=["flax_model.msgpack", "rust_model.ot", "tf_model.h5",],
)
os.rename(model_path_tmp, model_path)
Load
model=SentenceTransformer("/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit")
About
Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark"
Resources
Readme
Activity
Custom properties
Stars
18 stars
Watchers
1 watching
Forks
5 forks
Report repository
Releases
Packages
Contributors
Languages

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
GitHub - embeddings-benchmark/mtebpaper: Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark" · GitHub
Skip to content
BranchesTags
Repository files navigation
MTEB Paper resources
This repository contains scripts & resources for the MTEB paper. Some scripts rely on a results folder, which can be obtained via git clone https://huggingface.co/datasets/mteb/results. These scripts are unlikely to work with the latest version of MTEB but rather the 1.0.0 release when the paper was released; they are solely to ease reproduction of the original paper. Please refer to the MTEB repository for scripts and resources to work with the latest version and please open any issues with MTEB there; if you have issues with the original MTEB paper you can open them here.
Talks
Benchmark
Basic with Internet
frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
No Internet Access (Download data first)
importosos.environ["HF_DATASETS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_CACHE"]="/gpfswork/rech/six/commun/models"os.environ["HF_DATASETS_CACHE"]="/gpfswork/rech/six/commun/datasets"os.environ["HF_MODULES_CACHE"]="/gpfswork/rech/six/commun/modules"os.environ["HF_METRICS_CACHE"]="/gpfswork/rech/six/commun/metrics"frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
Env Setup
export CONDA_ENVS_PATH=$six_ALL_CCFRWORK/conda
conda create -y -n hf-prod python=3.8
conda activate hf-prod
# pt-1.10.1 / cuda 11.3
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# Custom fork that uses offline datasets!pip install --upgrade git+https://github.com/Muennighoff/mteb.git@offlineaccess
!pip install --upgrade git+https://github.com/Muennighoff/sentence-transformers.git@sgpt_poolings
# If you want to run BEIR tasks!pip install --upgrade git+https://github.com/beir-cellar/beir.git
Model setup
Download
importosimportsentence_transformersos.environ["SENTENCE_TRANSFORMERS_HOME"] ="/gpfswork/rech/six/commun/models"sentence_transformers_cache_dir=os.getenv("SENTENCE_TRANSFORMERS_HOME")
model_repo="sentence-transformers/allenai-specter"revision="29f9f45ff2a85fe9dfe8ce2cef3d8ec4e65c5f37"model_path=os.path.join(sentence_transformers_cache_dir, model_repo.replace("/", "_"))
model_path_tmp=sentence_transformers.util.snapshot_download(
repo_id=model_repo,
revision=revision,
cache_dir=sentence_transformers_cache_dir,
library_name="sentence-transformers",
library_version=sentence_transformers.__version__,
ignore_files=["flax_model.msgpack", "rust_model.ot", "tf_model.h5",],
)
os.rename(model_path_tmp, model_path)
Load
model=SentenceTransformer("/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit")
About
Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark"
Resources
Readme
Activity
Custom properties
Stars
18 stars
Watchers
1 watching
Forks
5 forks
Report repository
Releases
Packages
Contributors
Languages

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '
GitHub - embeddings-benchmark/mtebpaper: Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark" · GitHub
Skip to content
BranchesTags
Repository files navigation
MTEB Paper resources
This repository contains scripts & resources for the MTEB paper. Some scripts rely on a results folder, which can be obtained via git clone https://huggingface.co/datasets/mteb/results. These scripts are unlikely to work with the latest version of MTEB but rather the 1.0.0 release when the paper was released; they are solely to ease reproduction of the original paper. Please refer to the MTEB repository for scripts and resources to work with the latest version and please open any issues with MTEB there; if you have issues with the original MTEB paper you can open them here.
Talks
Benchmark
Basic with Internet
frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
No Internet Access (Download data first)
importosos.environ["HF_DATASETS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_CACHE"]="/gpfswork/rech/six/commun/models"os.environ["HF_DATASETS_CACHE"]="/gpfswork/rech/six/commun/datasets"os.environ["HF_MODULES_CACHE"]="/gpfswork/rech/six/commun/modules"os.environ["HF_METRICS_CACHE"]="/gpfswork/rech/six/commun/metrics"frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
Env Setup
export CONDA_ENVS_PATH=$six_ALL_CCFRWORK/conda
conda create -y -n hf-prod python=3.8
conda activate hf-prod
# pt-1.10.1 / cuda 11.3
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# Custom fork that uses offline datasets!pip install --upgrade git+https://github.com/Muennighoff/mteb.git@offlineaccess
!pip install --upgrade git+https://github.com/Muennighoff/sentence-transformers.git@sgpt_poolings
# If you want to run BEIR tasks!pip install --upgrade git+https://github.com/beir-cellar/beir.git
Model setup
Download
importosimportsentence_transformersos.environ["SENTENCE_TRANSFORMERS_HOME"] ="/gpfswork/rech/six/commun/models"sentence_transformers_cache_dir=os.getenv("SENTENCE_TRANSFORMERS_HOME")
model_repo="sentence-transformers/allenai-specter"revision="29f9f45ff2a85fe9dfe8ce2cef3d8ec4e65c5f37"model_path=os.path.join(sentence_transformers_cache_dir, model_repo.replace("/", "_"))
model_path_tmp=sentence_transformers.util.snapshot_download(
repo_id=model_repo,
revision=revision,
cache_dir=sentence_transformers_cache_dir,
library_name="sentence-transformers",
library_version=sentence_transformers.__version__,
ignore_files=["flax_model.msgpack", "rust_model.ot", "tf_model.h5",],
)
os.rename(model_path_tmp, model_path)
Load
model=SentenceTransformer("/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit")
About
Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark"
Resources
Readme
Activity
Custom properties
Stars
18 stars
Watchers
1 watching
Forks
5 forks
Report repository
Releases
Packages
Contributors
Languages

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
GitHub - embeddings-benchmark/mtebpaper: Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark" · GitHub
Skip to content
BranchesTags
Repository files navigation
MTEB Paper resources
This repository contains scripts & resources for the MTEB paper. Some scripts rely on a results folder, which can be obtained via git clone https://huggingface.co/datasets/mteb/results. These scripts are unlikely to work with the latest version of MTEB but rather the 1.0.0 release when the paper was released; they are solely to ease reproduction of the original paper. Please refer to the MTEB repository for scripts and resources to work with the latest version and please open any issues with MTEB there; if you have issues with the original MTEB paper you can open them here.
Talks
Benchmark
Basic with Internet
frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
No Internet Access (Download data first)
importosos.environ["HF_DATASETS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_CACHE"]="/gpfswork/rech/six/commun/models"os.environ["HF_DATASETS_CACHE"]="/gpfswork/rech/six/commun/datasets"os.environ["HF_MODULES_CACHE"]="/gpfswork/rech/six/commun/modules"os.environ["HF_METRICS_CACHE"]="/gpfswork/rech/six/commun/metrics"frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
Env Setup
export CONDA_ENVS_PATH=$six_ALL_CCFRWORK/conda
conda create -y -n hf-prod python=3.8
conda activate hf-prod
# pt-1.10.1 / cuda 11.3
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# Custom fork that uses offline datasets!pip install --upgrade git+https://github.com/Muennighoff/mteb.git@offlineaccess
!pip install --upgrade git+https://github.com/Muennighoff/sentence-transformers.git@sgpt_poolings
# If you want to run BEIR tasks!pip install --upgrade git+https://github.com/beir-cellar/beir.git
Model setup
Download
importosimportsentence_transformersos.environ["SENTENCE_TRANSFORMERS_HOME"] ="/gpfswork/rech/six/commun/models"sentence_transformers_cache_dir=os.getenv("SENTENCE_TRANSFORMERS_HOME")
model_repo="sentence-transformers/allenai-specter"revision="29f9f45ff2a85fe9dfe8ce2cef3d8ec4e65c5f37"model_path=os.path.join(sentence_transformers_cache_dir, model_repo.replace("/", "_"))
model_path_tmp=sentence_transformers.util.snapshot_download(
repo_id=model_repo,
revision=revision,
cache_dir=sentence_transformers_cache_dir,
library_name="sentence-transformers",
library_version=sentence_transformers.__version__,
ignore_files=["flax_model.msgpack", "rust_model.ot", "tf_model.h5",],
)
os.rename(model_path_tmp, model_path)
Load
model=SentenceTransformer("/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit")
About
Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark"
Resources
Readme
Activity
Custom properties
Stars
18 stars
Watchers
1 watching
Forks
5 forks
Report repository
Releases
Packages
Contributors
Languages

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
GitHub - embeddings-benchmark/mtebpaper: Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark" · GitHub
Skip to content
BranchesTags
Repository files navigation
MTEB Paper resources
This repository contains scripts & resources for the MTEB paper. Some scripts rely on a results folder, which can be obtained via git clone https://huggingface.co/datasets/mteb/results. These scripts are unlikely to work with the latest version of MTEB but rather the 1.0.0 release when the paper was released; they are solely to ease reproduction of the original paper. Please refer to the MTEB repository for scripts and resources to work with the latest version and please open any issues with MTEB there; if you have issues with the original MTEB paper you can open them here.
Talks
Benchmark
Basic with Internet
frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
No Internet Access (Download data first)
importosos.environ["HF_DATASETS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_CACHE"]="/gpfswork/rech/six/commun/models"os.environ["HF_DATASETS_CACHE"]="/gpfswork/rech/six/commun/datasets"os.environ["HF_MODULES_CACHE"]="/gpfswork/rech/six/commun/modules"os.environ["HF_METRICS_CACHE"]="/gpfswork/rech/six/commun/metrics"frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
Env Setup
export CONDA_ENVS_PATH=$six_ALL_CCFRWORK/conda
conda create -y -n hf-prod python=3.8
conda activate hf-prod
# pt-1.10.1 / cuda 11.3
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# Custom fork that uses offline datasets!pip install --upgrade git+https://github.com/Muennighoff/mteb.git@offlineaccess
!pip install --upgrade git+https://github.com/Muennighoff/sentence-transformers.git@sgpt_poolings
# If you want to run BEIR tasks!pip install --upgrade git+https://github.com/beir-cellar/beir.git
Model setup
Download
importosimportsentence_transformersos.environ["SENTENCE_TRANSFORMERS_HOME"] ="/gpfswork/rech/six/commun/models"sentence_transformers_cache_dir=os.getenv("SENTENCE_TRANSFORMERS_HOME")
model_repo="sentence-transformers/allenai-specter"revision="29f9f45ff2a85fe9dfe8ce2cef3d8ec4e65c5f37"model_path=os.path.join(sentence_transformers_cache_dir, model_repo.replace("/", "_"))
model_path_tmp=sentence_transformers.util.snapshot_download(
repo_id=model_repo,
revision=revision,
cache_dir=sentence_transformers_cache_dir,
library_name="sentence-transformers",
library_version=sentence_transformers.__version__,
ignore_files=["flax_model.msgpack", "rust_model.ot", "tf_model.h5",],
)
os.rename(model_path_tmp, model_path)
Load
model=SentenceTransformer("/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit")
About
Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark"
Resources
Readme
Activity
Custom properties
Stars
18 stars
Watchers
1 watching
Forks
5 forks
Report repository
Releases
Packages
Contributors
Languages

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();
GitHub - embeddings-benchmark/mtebpaper: Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark" · GitHub
Skip to content
BranchesTags
Repository files navigation
MTEB Paper resources
This repository contains scripts & resources for the MTEB paper. Some scripts rely on a results folder, which can be obtained via git clone https://huggingface.co/datasets/mteb/results. These scripts are unlikely to work with the latest version of MTEB but rather the 1.0.0 release when the paper was released; they are solely to ease reproduction of the original paper. Please refer to the MTEB repository for scripts and resources to work with the latest version and please open any issues with MTEB there; if you have issues with the original MTEB paper you can open them here.
Talks
Benchmark
Basic with Internet
frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
No Internet Access (Download data first)
importosos.environ["HF_DATASETS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_OFFLINE"]="1"# 1 for offlineos.environ["TRANSFORMERS_CACHE"]="/gpfswork/rech/six/commun/models"os.environ["HF_DATASETS_CACHE"]="/gpfswork/rech/six/commun/datasets"os.environ["HF_MODULES_CACHE"]="/gpfswork/rech/six/commun/modules"os.environ["HF_METRICS_CACHE"]="/gpfswork/rech/six/commun/metrics"frommtebimportMTEBfromsentence_transformersimportSentenceTransformermodel_path="/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit"model_name=model_path.split("/")[-1].split("_")[-1]
model=SentenceTransformer(model_path)
evaluation=MTEB(tasks=["Banking77Classification"])
evaluation.run(model, output_folder=f"results/{model_name}")
Env Setup
export CONDA_ENVS_PATH=$six_ALL_CCFRWORK/conda
conda create -y -n hf-prod python=3.8
conda activate hf-prod
# pt-1.10.1 / cuda 11.3
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# Custom fork that uses offline datasets!pip install --upgrade git+https://github.com/Muennighoff/mteb.git@offlineaccess
!pip install --upgrade git+https://github.com/Muennighoff/sentence-transformers.git@sgpt_poolings
# If you want to run BEIR tasks!pip install --upgrade git+https://github.com/beir-cellar/beir.git
Model setup
Download
importosimportsentence_transformersos.environ["SENTENCE_TRANSFORMERS_HOME"] ="/gpfswork/rech/six/commun/models"sentence_transformers_cache_dir=os.getenv("SENTENCE_TRANSFORMERS_HOME")
model_repo="sentence-transformers/allenai-specter"revision="29f9f45ff2a85fe9dfe8ce2cef3d8ec4e65c5f37"model_path=os.path.join(sentence_transformers_cache_dir, model_repo.replace("/", "_"))
model_path_tmp=sentence_transformers.util.snapshot_download(
repo_id=model_repo,
revision=revision,
cache_dir=sentence_transformers_cache_dir,
library_name="sentence-transformers",
library_version=sentence_transformers.__version__,
ignore_files=["flax_model.msgpack", "rust_model.ot", "tf_model.h5",],
)
os.rename(model_path_tmp, model_path)
Load
model=SentenceTransformer("/gpfswork/rech/six/commun/models/Muennighoff_SGPT-125M-weightedmean-nli-bitfit")
About
Resources & scripts for the paper "MTEB: Massive Text Embedding Benchmark"
Resources
Readme
Activity
Custom properties
Stars
18 stars
Watchers
1 watching
Forks
5 forks
Report repository
Releases
Packages
Contributors
Languages