tiiuae/falcon-7b-instruct

Fine tuning "nRuntimeError: weight transformer.word_embeddings.weight does not exist"

1

#64 opened over 1 year ago by

rshrott

Repeats the same sentence

4

#62 opened over 1 year ago by

fatimataayeb

UnexpectedStatusException: Error hosting endpoint huggingface-pytorch-tgi-inference-2023-07-12-08-18-29-406

5

#61 opened over 1 year ago by

pranavnerurkar

Help! Unable to deploy Falcon 7b Instruct on AWS Sagemaker

3

#59 opened over 1 year ago by

np05

Performance reduction from using 8bit or 4bit quantized model

#58 opened over 1 year ago by

michaelomahony

Problem in loading falcon-7b-instruct locally

3

#57 opened over 1 year ago by

Yash2k23

Add `tokenizer_class` to get `pipeline` to load tokenizer

#54 opened over 1 year ago by

chiragjn

Adding `safetensors` variant of this model

#53 opened over 1 year ago by

kiranshivaraju

Blogpost for falcon not working

#52 opened over 1 year ago by

ziadnader1

Adding `safetensors` variant of this model

#51 opened over 1 year ago by

CalebAtkins

Adding `safetensors` variant of this model

#50 opened over 1 year ago by

CalebAtkins

Is this model commercially usable?

1

#49 opened almost 2 years ago by

AayushShah

Error in loading falcon-7b-instruct

18

#48 opened almost 2 years ago by

gtmanuj

unable to use falcon-7b-instruct using transformers

2

#47 opened almost 2 years ago by

subhashhf

Fix link to blog post

#46 opened almost 2 years ago by

pcuenq

Fix minor typo

#45 opened almost 2 years ago by

pcuenq

Internal Server Error - (Falcon-7B-Instruct)

#44 opened almost 2 years ago by

divyaAI

Output formatting not enforceable

1

#43 opened almost 2 years ago by

Rick458

Update README.md

#41 opened almost 2 years ago by

saattrupdan

Generated text frequently ends with 'User'

5

#40 opened almost 2 years ago by

tolgaakar

Adding `safetensors` variant of this model

1

#39 opened almost 2 years ago by

makeColabFree

Benchmarks on performance

1

#38 opened almost 2 years ago by

ptrrrr

Error following starter code

#37 opened almost 2 years ago by

eskayML

Double amount of memory usage when calling generate function (inference)

#36 opened almost 2 years ago by

isaranto

Repo ID HFValidationError for RWModel(

7

#35 opened almost 2 years ago by

patti-j

any success in In-context question-answering?

1

#34 opened almost 2 years ago by

beejay

Slow inference

9

#33 opened almost 2 years ago by

BigArt

Converting falcon-7b-instruct to binaries using fastertransformer to serve in triton server

#32 opened almost 2 years ago by

ankitsingh1996

4th inference in a row does not work for Falcon7B in 8 or 4 bit

2

#31 opened almost 2 years ago by

max0uu

what is the prompt used for instruction tuning, and why the model is pre-trained on refineweb but also instruction-tuned with it?

3

#30 opened almost 2 years ago by

zerolyn

[Need Help] Would this model work if the input to this model is padded?

#27 opened almost 2 years ago by

vivek0797

Loading ./pipeline/ requires you to execute the configuration file in that repo on your local machine

9

#21 opened almost 2 years ago by

kycrowe

not enough values to unpack (expected 4, got 3)

8

#19 opened almost 2 years ago by

srinivasbilla

max_length not working?

4

#18 opened almost 2 years ago by

domid10

Model keeps generating multiple rounds of conversation

5

#17 opened almost 2 years ago by

nomorewords

Deployment to Amazon SageMaker - `trust_remote_code` issue

3

#10 opened almost 2 years ago by

dgallitelli

ValueError: not enough values to unpack (expected 4, got 3)

1

#6 opened almost 2 years ago by

veilsidebr

8bit and sharded weights

3

#5 opened almost 2 years ago by

ThreeBlessings

How use it with LangChain Library

1

#4 opened almost 2 years ago by

tarungupta83