intfloat
/

e5-mistral-7b-instruct

Feature Extraction

sentence-transformers

text-embeddings-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (13)

Question about MTEB Evaluation and max_seq_length Settings for e5-mistral-7b-instruct

#47 opened 9 days ago by

Is it possible to change the dimentions of the embeddings it generates?

#46 opened 2 months ago by

Adding `safetensors` variant of this model

#45 opened 6 months ago by

Best Practices for Fine-Tuning Models on Multi-Hop Datasets?

#43 opened 7 months ago by

How to set instruct for MRACL dataset?

#41 opened 8 months ago by

CUDA Memory error when using sentence transformers using Tesla V100-PCIE-32GB

#40 opened 8 months ago by

How did you construct homogeneous batch if there is not enough sample to make single batch?

#38 opened 8 months ago by

Can anyone help on this phenomenon? Fine tuning intfloat / e5-mistral-7b-instruct got nan loss and all NaN intermediate model outputs

#37 opened 8 months ago by

Use in sentence transformers

#35 opened 9 months ago by

Understanding memory consumption during inference

#34 opened 9 months ago by

Questions about the training data

#33 opened 10 months ago by

How much GPU memory is required for 32k context embedding?

#32 opened 10 months ago by

Quantization

#30 opened 10 months ago by

Train loss for reproduction

#29 opened 10 months ago by

Is there a way to do fine tuning using STS datasets?

#27 opened 11 months ago by

Instruction / Query document embedding question.

#26 opened 11 months ago by

KeyError: 'mistral' Application startup failed during deployment on Inference Endpoints

#24 opened 11 months ago by

best way to deploy this as an API endpoint.

#21 opened 11 months ago by

Error using multiple GPUs

#20 opened 11 months ago by

Can you tell me the detail about negative sampling for benchmark data?

#19 opened 11 months ago by

Deployment fails (weight model.embed_tokens.weight does not exist) to Inference Endpoint

#18 opened 11 months ago by

how to extract general text embedding

#17 opened 11 months ago by

Is it possible to convert the model to ONNX?

#16 opened 11 months ago by

About max sequence length

#14 opened 12 months ago by

Knowledge distillation into smaller model

#13 opened 12 months ago by

RuntimeError: weight model.embed_tokens.weight does not exist

#12 opened 12 months ago by

When should I use this instruction for RAG retrival tasks?

#11 opened 12 months ago by

Hardware Requirements

#10 opened 12 months ago by

Can you training a multilingual e5 based on a multilingual LLM?

#9 opened 12 months ago by

symmetric tasks prompts

#8 opened 12 months ago by

Any plan to release fine-tuning scripts?

#7 opened 12 months ago by

lora config

#6 opened 12 months ago by

Any plan to release training data?

#3 opened 12 months ago by

MLX example

#1 opened 12 months ago by

paulmaksimovich