Hugging Face's logo
Liang Wang's picture
134 2 24

Liang Wang

intfloat
smg478's profile picture rkennezangue's profile picture Mouli's profile picture
·
https://www.microsoft.com/en-us/research/people/wangliang/
intfloat

AI & ML interests

natural language processing

Organizations

Microsoft's profile picture SGPT2's profile picture GritLM's profile picture

intfloat's activity

New activity in intfloat/multilingual-e5-large 16 days ago

Weak supervision on mc4

1
#37 opened 17 days ago by yuri-no
New activity in intfloat/multilingual-e5-large 24 days ago

Unclear query and passage prefix instructions

4
#34 opened 2 months ago by Avditvs
New activity in intfloat/e5-mistral-7b-instruct about 1 month ago

How to set instruct for MRACL dataset?

1
#41 opened about 1 month ago by Mengyao00

Simplify usage; integrate Sentence Transformers (+ LlamaIndex/LangChain, etc.)

3
#39 opened about 1 month ago by tomaarsen
New activity in intfloat/e5-mistral-7b-instruct 3 months ago

Understanding memory consumption during inference

2
#34 opened 3 months ago by andrew-kirfman
New activity in intfloat/wikidata5m 3 months ago

Hello! What's this meant to be used for?

1
#1 opened 3 months ago by metasj
New activity in intfloat/multilingual-e5-base 3 months ago

Model can't be moved to GPU

2
#20 opened 3 months ago by ftopal
New activity in intfloat/multilingual-e5-large-instruct 3 months ago

On the usage and creation of E5-instruct embeddings

2
#8 opened 3 months ago by jmaronasm
New activity in intfloat/e5-mistral-7b-instruct 3 months ago

Questions about the training data

4
#33 opened 3 months ago by xxxcliu
New activity in intfloat/multilingual-e5-large 3 months ago

Finetuning on burmese text?

1
#31 opened 3 months ago by Myogyi
New activity in intfloat/e5-mistral-7b-instruct 3 months ago

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

1
#32 opened 3 months ago by Labmem009
New activity in intfloat/multilingual-e5-large-instruct 3 months ago

Cuda Error when using with HuggingFaceEmbedding of llamaindex

2
#7 opened 3 months ago by glpcc
commented a paper 3 months ago
New activity in intfloat/e5-mistral-7b-instruct 3 months ago

How to integreate this model with Sentence Transformers?

6
#31 opened 3 months ago by Nelson365487
New activity in intfloat/multilingual-e5-large-instruct 3 months ago

Missing `sentence_bert_config.json`

1
#5 opened 3 months ago by viethang
New activity in intfloat/multilingual-e5-base 3 months ago

Single jar file for Java access to the intfloat/multilingual-e5-base model/data to avoid dynamic loading vulnerabilities

4
#19 opened 3 months ago by wnmills3
New activity in intfloat/multilingual-e5-large-instruct 4 months ago

Dataset publication & questions

2
#3 opened 4 months ago by tomaarsen
New activity in intfloat/multilingual-e5-large 4 months ago

Finetuning: Problem with dense similarity scores (0.7 .. 1.0) ?

1
#30 opened 4 months ago by drdsgvo
New activity in intfloat/multilingual-e5-large-instruct 4 months ago

Is Instruct and Query are keywords or we can use any?

2
#4 opened 4 months ago by Talha

Add Sentence Transformers support

1
#2 opened 4 months ago by tomaarsen

Add link to new paper
#1 opened 4 months ago by osanseviero
New activity in intfloat/multilingual-e5-base 4 months ago

Add link to new paper
#18 opened 4 months ago by osanseviero
New activity in intfloat/multilingual-e5-small 4 months ago

Add link to new paper
#7 opened 4 months ago by osanseviero
New activity in intfloat/e5-mistral-7b-instruct 4 months ago

minimal example with flash attention

2
#28 opened 4 months ago by keepitsane
New activity in intfloat/multilingual-e5-large 4 months ago

Add link to new paper

1
#29 opened 4 months ago by osanseviero
New activity in intfloat/e5-mistral-7b-instruct 4 months ago

Instruction / Query document embedding question.

2
#26 opened 4 months ago by eek
New activity in intfloat/multilingual-e5-base 4 months ago

Embeddings and Cosine Similarity

3
#17 opened 4 months ago by karmiq
New activity in intfloat/multilingual-e5-large 4 months ago

Checkpoint of the first stage

1
#28 opened 4 months ago by YuTian8328
New activity in intfloat/e5-mistral-7b-instruct 4 months ago

Sample ratio for training data

3
#25 opened 4 months ago by coverwhole

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

1
#24 opened 4 months ago by hoangsx

Safetensor keys differ with mistralai/Mistral-7B-v0.1

2
#23 opened 4 months ago by functorism

How to embed 5 Million documents?

2
#22 opened 4 months ago by leonshub
commented a paper 4 months ago
New activity in intfloat/e5-mistral-7b-instruct 4 months ago

best way to deploy this as an API endpoint.

12
#21 opened 4 months ago by aigeek0x0
New activity in intfloat/multilingual-e5-large 4 months ago

Maximum Chunk Size for RAG

2
#27 opened 4 months ago by mox
New activity in intfloat/e5-mistral-7b-instruct 4 months ago

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

2
#19 opened 4 months ago by lightapple

Error using multiple GPUs

4
#20 opened 4 months ago by JesusUned

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

5
#18 opened 4 months ago by ts314
New activity in intfloat/e5-mistral-7b-instruct 5 months ago

Is it possible to convert the model to ONNX?

1
#16 opened 5 months ago by serdarcaglar

Lora adapter version

2
#15 opened 5 months ago by thomasgauthier

Knowledge distillation into smaller model

2
#13 opened 5 months ago by tomaarsen

RuntimeError: weight model.embed_tokens.weight does not exist

6
#12 opened 5 months ago by ivankeller

When should I use this instruction for RAG retrival tasks?

5
#11 opened 5 months ago by kk3dmax

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

3
#9 opened 5 months ago by hantian

Hardware Requirements

4
#10 opened 5 months ago by Ravnoor1

symmetric tasks prompts

1
#8 opened 5 months ago by mayjacky
New activity in intfloat/multilingual-e5-large 5 months ago

File Size

3
#24 opened 5 months ago by Eigenket27
New activity in intfloat/e5-mistral-7b-instruct 5 months ago

Any plan to release fine-tuning scripts?

4
#7 opened 5 months ago by Mengyao00
New activity in intfloat/multilingual-e5-large 5 months ago

Fine tuning on esci data

1
#25 opened 5 months ago by yklymchuk-rztk
New activity in intfloat/e5-mistral-7b-instruct 5 months ago

lora config

1
#6 opened 5 months ago by SeanLee97

Temperature-scaled cosine similarity function?

3
#4 opened 5 months ago by nalzok

Adding `safetensors` variant of this model
#5 opened 5 months ago by SFconvertbot

Any plan to release training data?

3
#3 opened 5 months ago by memray

Technical paper?

1
#2 opened 5 months ago by fagbavor

MLX example

3
#1 opened 5 months ago by paulmaksimovich
New activity in intfloat/simlm-msmarco 6 months ago

Where to find negative passages by the 'doc_id' provided?

1
#2 opened 6 months ago by Mengyao00
New activity in intfloat/multilingual-e5-base 6 months ago

Semantic Search

5
#14 opened 6 months ago by dilolo

Adding ONNX file of this model

1
#13 opened 6 months ago by egiacoletto
New activity in intfloat/multilingual-e5-large 7 months ago

Fine tuning for a dutch forum.

7
#21 opened 7 months ago by Ziizu

Memory leak(memory increasing slowly in each inference in cpu)

1
#19 opened 7 months ago by scancet