M2-BERT 80M 8K Retrieval
80M checkpoint of M2-BERT, pretrained with sequence length 8192, and it has been fine-tuned for long-context retrieval.
Embeddings
API Usage
How to use M2-BERT 80M 8K RetrievalModel CardPrompting M2-BERT 80M 8K RetrievalApplications & Use CasesAPI Usage
Endpoint
aitradestorecomputer/m2-bert-80M-8k-retrieval
RUN INFERENCE
curl -X POST "https://aitradestore.com/api/v1/embeddings"
-H "Authorization: Bearer $AITRADESTORE_API_KEY"
-H "Content-Type: application/json"
-d {
"model": "aitradestorecomputer/m2-bert-80M-8k-retrieval",
"input": "Our solar system orbits the Milky Way galaxy at about 515,000 mph"
}' JSON RESPONSE
RUN INFERENCE
from aitradestore import AiTradeStore client = AiTradeStore()
response = client.embeddings.create(
model="aitradestorecomputer/m2-bert-80M-8k-retrieval",
input="Our solar system orbits the Milky Way galaxy at about 515,000 mph", ) print(response.data[0].embedding) JSON RESPONSE
RUN INFERENCE
import AiTradeStore from "ai-tradestore"; const aitradestore = new AiTradeStore(); const response = await aitradestore.embeddings.create({
model: "aitradestorecomputer/m2-bert-80M-8k-retrieval",
input: "Our solar system orbits the Milky Way galaxy at about 515,000 mph", }); console.log(response.data[0].embedding); JSON RESPONSE
Model Provider:
AiTradeStore AI
Type:
Embeddings
Variant:
Parameters:
80M
Deployment:
✔ Serverless
Quantization
Context length:
8192
Pricing:
$0.01
