Falcon LLM TII UAE

New activity in tiiuae/falcon-rw-1b about 1 year ago

Move to in-library checkpoint

#4 opened about 1 year ago by

New activity in tiiuae/falcon-7b-instruct about 1 year ago

Move to in-library checkpoint

#56 opened about 1 year ago by

New activity in tiiuae/falcon-7b about 1 year ago

Move to in-library checkpoint

#57 opened about 1 year ago by

New activity in tiiuae/falcon-40b-instruct about 1 year ago

Move to in-library checkpoint

#60 opened about 1 year ago by

New activity in tiiuae/falcon-40b about 1 year ago

Move to in-library checkpoint

#81 opened about 1 year ago by

New activity in tiiuae/falcon-40b-instruct about 1 year ago

Upload Отчет_Системный_Индекс_счастья_Medical_Case.pdf

#34 opened about 1 year ago by

Romanzar

a100-80g memory but still call error

6

#32 opened about 1 year ago by

leocheung

how to implement multiquery, FlashAttention and alibi.

#29 opened about 1 year ago by

NickyNicky

Why not add system requirements on the model card?

9

#28 opened about 1 year ago by

johnjohndoedoe

Getting "trust_remote_code" Error when Running SageMaker Deploy Code Sample

#27 opened about 1 year ago by

garystafford

Fix "Finetuned from model" link

#26 opened about 1 year ago by

rocca

Finetuned from model: Falcon-7B???

#25 opened about 1 year ago by

DrNicefellow

Caching doesn't work on multi gpu

#23 opened about 1 year ago by

eastwind

How to finetune the falcon-40b

#21 opened about 1 year ago by

jiangix

Slow and Gibberish when inferencing

11

#20 opened about 1 year ago by

eastwind

Is there a way to control the temperature of the model?

#19 opened about 1 year ago by

zkdtckk

Update README.md: Update Model Description to reference Falcon-40B as the base model for falcon-40b-instruct

#17 opened about 1 year ago by

AliSab

SageMaker Endpoint error during inference

12

#16 opened about 1 year ago by

Shridharalve

Response language issue with fastchat

#14 opened about 1 year ago by

manishl127

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

#9 opened about 1 year ago by

rmihaylov

How to try Flacon in HuggingChat?

5

#6 opened about 1 year ago by

promptgai

New activity in tiiuae/falcon-40b about 1 year ago

Might be interesting to have a thread on people with Successful Implementations, and on what kind of hardware..

#53 opened about 1 year ago by

LinuxMagic

What is the inference time? Any ideas how to make it faster?

#52 opened about 1 year ago by

leoapolonio

Is it really Good ?

#51 opened about 1 year ago by

a749734

multiquery attention

#46 opened about 1 year ago by

ZhongYingMatrix

Could you share the full pretraining data of Falcon-40B

#45 opened about 1 year ago by

ChangranHuuu

how much Vram does it take to run Falcon 40b

7

#44 opened about 1 year ago by

Toaster496

Question: Not support Arabic.

#43 opened about 1 year ago by

awyshen

Add hf endpoint handler

#42 opened about 1 year ago by

olivierdehaene

Update README.md

#40 opened about 1 year ago by

roboojack

Falcon 40B Inference at 4bit in Google Colab

27

#38 opened about 1 year ago by

serin32

In addition to task 'text-generation', can falcon be used for other tasks like summarization, QA etc?

#37 opened about 1 year ago by

VS9205

Fine-tuning on a new language

#35 opened about 1 year ago by

AliMirlou

Plans for other versions (outside of 7B and 40B)?

#26 opened about 1 year ago by

flashvenom

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

6

#25 opened about 1 year ago by

rmihaylov

Working code with full server requirements

#24 opened about 1 year ago by

gmjolt

Fine Tuning examples

#21 opened about 1 year ago by

skeenan947

Finetune wtih QLoRA please

7

#14 opened about 1 year ago by

supercharge19

How to set trust_remote_code to true?

13

#9 opened about 1 year ago by

gmjolt

[Bug] Does not work

58

#3 opened about 1 year ago by

catid

New activity in tiiuae/falcon-7b-instruct about 1 year ago

Tried to allocate 564.00 MiB (GPU 0; 7.98 GiB total capacity; 7.52 GiB already allocated; 446.00 MiB free; 7.55 GiB reserved in total by PyTorch)

#25 opened about 1 year ago by

davisitoo

memory needed

#23 opened about 1 year ago by

koshinryuu

CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling `cublasGemmStridedBatchedFx...

#20 opened about 1 year ago by

CalumPlays

ValueError: The following `model_kwargs` are not used by the model: ['token_type_ids'] (note: typos in the generate arguments will also show up in this list)

#2 opened about 1 year ago by

Imran1

Sample code error - AttributeError: module 'torch.nn.functional' has no attribute 'scaled_dot_product_attention'

#16 opened about 1 year ago by

bernardogmorais

Ambiguous License

#15 opened about 1 year ago by

jdpressman

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

#13 opened about 1 year ago by

rmihaylov

Is it possible to generate semantic embeddings?

#12 opened about 1 year ago by

michael-newsrx-com

Deployment to Amazon SageMaker - `trust_remote_code` issue

#10 opened about 1 year ago by

dgallitelli

Getting an error with the example code

16

#7 opened about 1 year ago by

aviadatlas

8bit and sharded weights

#5 opened about 1 year ago by

ThreeBlessings

New activity in tiiuae/falcon-7b about 1 year ago

How to quantize this model using QLoRA ?

#7 opened about 1 year ago by

mrhimanshu

Error when using falcon-7b model for embeddings

#25 opened about 1 year ago by

Shilpil

How to make it work for less experienced AI whisperers

17

#4 opened about 1 year ago by

Sloba

Support for LoRA?

17

#3 opened about 1 year ago by

cekal

Spell correction

#22 opened about 1 year ago by

surajp

Is it possible to add TF Weights

#21 opened about 1 year ago by

mb-data96

Add hf endpoint handler.py