tiiuae/falcon-7b-instruct

Custom 4-bit Finetuning 5-7 times faster inference than QLora

pinned

#13 opened 6 months ago by

rmihaylov

Example Use

pinned

29

#1 opened 7 months ago by

Supreeth

Can Falcon have supported UTF-8?

#110 opened 17 days ago by

vutruc

No package metadata was found for bitsandbytes

#109 opened 19 days ago by

Fyutong

Adding Evaluation Results

#108 opened 22 days ago by

leaderboard-pr-bot

Compare Multiple Document using this model.

#104 opened 25 days ago by

Pitambarmuduli

Upload model

#103 opened 26 days ago by

dookplaza

Reasearch team in Nile university.

#101 opened about 1 month ago by

kirollossaleh

This is an instruct model, which may not be ideal for further finetuning.

1

#100 opened about 1 month ago by

rakeshda

tiiuae/falcon-7b-instruct does not appear to have a file named config.json

#99 opened about 1 month ago by

robotrage

falcon-7b-instruct responds with weird and short answers ?

#98 opened about 1 month ago by

olsi8

model not generating text

#97 opened about 1 month ago by

airedwin

Trying to deploy this using Inference Endpoints

1

#96 opened about 1 month ago by

Kolibri753

Code for using inference api

#94 opened about 2 months ago by

Karthik2003

Inference Api

#93 opened about 2 months ago by

Karthik2003

The correctness of the result using transformers apply_chat_template

1

#92 opened about 2 months ago by

Annorita

Request: DOI

#91 opened 2 months ago by

binbin888

How is falcon able to generate indic token , when it is not trained on Indic languages. even tokenizer.json doest have any Indic tokens.

#90 opened 2 months ago by

Sibadatta

How to solve this issue?

#87 opened 3 months ago by

Xiaogeng-SheltonLiu

Update generation_config.json

1

#86 opened 3 months ago by

nkasmanoff

Adding `safetensors` variant of this model

#84 opened 3 months ago by

bharathrajcl

Hardware requirements on falcon models: 7B, 40B, 180B

2

#83 opened 3 months ago by

its-eric-liu

Switching Falcon to other language

#82 opened 3 months ago by

wokalove

Update config.json

#81 opened 3 months ago by

Daniil-plotnikov

'num_return_sequences' & 'num_beams' can't be changed in inference API calls

#80 opened 3 months ago by

mrscoopers

Adding `safetensors` variant of this model

#79 opened 3 months ago by

bikalnetomi

Facing Issues with Model Output and Inference Times

1

#78 opened 3 months ago by

ankity09

License file

#77 opened 3 months ago by

jsaurabh

Share your recommended configurations for speed.

#76 opened 4 months ago by

archonlith

Adding `safetensors` variant of this model

#75 opened 4 months ago by

Shridharalve

Use input attention mask instead of casual mask in attention

#74 opened 4 months ago by

CyberZHG

Merge SentenceTransformer with Falcon-7b-instruct

#73 opened 4 months ago by

Alkahwaji

integration issue with Langchain csv agent

2

#71 opened 4 months ago by

DanCher

Issue with Falcon LLM while trying to use it on AWS EC2 Inferentia 2.8xlarge Instance

#70 opened 5 months ago by

AmlanSamanta

while giving a input but getting the wrong output for the particular input

#69 opened 5 months ago by

saidheer

Getting message Killed when loading on multi-gpu

2

#68 opened 5 months ago by

jurecucek

falcon in node.js

#67 opened 5 months ago by

othman95

falcon-7b-instruct is answering out of context

#66 opened 5 months ago by

kvmukilan

How to use the CoreML model?

5

#65 opened 5 months ago by

yyjhao

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

1

#64 opened 5 months ago by

rshrott

Repeats the same sentence

4

#62 opened 5 months ago by

fatimataayeb

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

5

#61 opened 5 months ago by

pranavnerurkar

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

3

#59 opened 5 months ago by

np05

Performance reduction from using 8bit or 4bit quantized model

#58 opened 5 months ago by

michaelomahony

Problem in loading falcon-7b-instruct locally

3

#57 opened 5 months ago by

Yash2k23

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

#54 opened 5 months ago by

chiragjn

Adding `safetensors` variant of this model

#53 opened 5 months ago by

kiranshivaraju

Blogpost for falcon not working

#52 opened 5 months ago by

ziadnader1

Adding `safetensors` variant of this model

#51 opened 5 months ago by

CalebAtkins

Adding `safetensors` variant of this model

#50 opened 5 months ago by

CalebAtkins