nvidia/NV-Embed-v1 · Discussions

#45 opened 12 months ago by

lukelv

Batch_size

#44 opened 12 months ago by

lukelv

replicate experimental results on the MTEB dataset

#42 opened 12 months ago by

lzq2021

Code trying to download model from huggingface instead of using Locally Downloaded Model

4

#41 opened 12 months ago by

sharedJackpot

Model Loading Error

#40 opened 12 months ago by

kcsham

Supporting Flash Attention 2.0

#39 opened 12 months ago by

Cdemir

'MistralModel' object has no attribute 'encode'

#38 opened about 1 year ago by

dadada

Has the tokenizer of the base model(Mistral-7B-v0.1) been retrained?

#37 opened about 1 year ago by

LH0521

How did you trained your LatentAttentionLayer?

#36 opened about 1 year ago by

juneonetwothree

Why do we need to hardcode self._attn_implementation = "eager"

#35 opened about 1 year ago by

shantanuagarwal

Error to load model with HuggingFace API

#34 opened about 1 year ago by deleted

Regarding max seq length

#33 opened about 1 year ago by

sandeep456

How to fine-tune this model?

👀 ➕ 23

#32 opened about 1 year ago by

caochengchen

error with module datasets

#31 opened about 1 year ago by

claraadam

Distant resource does not have a Content-Length

#30 opened about 1 year ago by

caochengchen

Best instructions for clustering and semantic similarity

#29 opened about 1 year ago by

rmilliere

Dataloader multiprocessing error

#28 opened about 1 year ago by

Atsunori

Fixing "KeyError: 'NVEmbedConfig'"

10

#27 opened about 1 year ago by

Th3l

Error using multi-gpu support

5

#26 opened about 1 year ago by

bobwhiterabbit

Access to model nvidia/NV-Embed-v1 is restricted. You must be authenticated to access it

6

#25 opened about 1 year ago by

yijiu

Matryoshka Embedding

#24 opened about 1 year ago by

XingyanZhang

nvidia/NV-Embed-v1 is not the path to a directory containing a file named config.json.

#23 opened about 1 year ago by

XuehangCang

Finetuning guidelines

👀 🚀 5

#21 opened about 1 year ago by

mali404

How much VRAM is needed to run this model? Like for the bare minimum length etc?

#20 opened about 1 year ago by

smpa239

Ollama Version

#19 opened about 1 year ago by

yangwang825

Weights are in FP16 (loaded in FP32) but paper mentions BF16

👍 6

#17 opened about 1 year ago by

AdrienC

ONNX version

#16 opened about 1 year ago by

michaelfeil

Sentence Transformer compatibility

4

#15 opened about 1 year ago by

michaelfeil

Please provide a 8bit quantified version

👍 👀 4

#14 opened about 1 year ago by

fukai

How to use for AutoModelForSequenceClassification?

👍 5

#13 opened about 1 year ago by

deshwalmahesh

Possible to implement `_no_split_modules` attribute?

#12 opened about 1 year ago by

ronnybehrens

missing citation

#11 opened about 1 year ago by

SeanLee97

Multi-Lingual?

#10 opened about 1 year ago by

dejanseo

Getting "KeyError" when loading model

5

#8 opened about 1 year ago by

tsakaiba

TypeError: MistralDecoderLayer.forward() got an unexpected keyword argument 'is_causal'

#7 opened about 1 year ago by

yxzwayne

Is this model active?

#5 opened about 1 year ago by

gsnic

Sharing training data & reproducing training

🤝 6