tiiuae/falcon-40b-instruct

#9 opened almost 2 years ago by

rmihaylov

Update tokenizer_config.json

#92 opened about 1 month ago by

Snanni

Update tokenizer_config.json

#91 opened about 1 month ago by

Maryammmmmm

falcon-40b-instruct error on Inference endpoint while deploying

#90 opened 3 months ago by

digitalsanjeev

AI World

#89 opened 11 months ago by

MohammadMuzamil

Adding `safetensors` variant of this model

#88 opened about 1 year ago by

Dennison33

combining falcon 40b instruct with langchain

#87 opened about 1 year ago by

rra21

Update generation_config.json

#85 opened over 1 year ago by

nkasmanoff

Update generation_config.json

#84 opened over 1 year ago by

nkasmanoff

Getting gibberish output with Falcon-40b instruct

#83 opened over 1 year ago by

harsh244

Falcon 40B Inference on GKE Autopilot A100 40GB

#82 opened over 1 year ago by

bshongwe

Adding `safetensors` variant of this model

#81 opened over 1 year ago by

Flolight

Adding `safetensors` variant of this model

#80 opened over 1 year ago by

Flolight

CPU or GPU

#76 opened over 1 year ago by

lalit34

Optimizing Inference Time for Chat Conversations on Falcon

#73 opened over 1 year ago by

humza-sami

Use input attention mask instead of casual mask in attention

#72 opened over 1 year ago by

CyberZHG

is there a way to not use trust_remote = True

#71 opened over 1 year ago by

momentumhd

Unable to load and run finetuned falcon model

#70 opened over 1 year ago by

DioulaD

Parameters contains nan numbers when loading model locally

#69 opened over 1 year ago by

yunsxie

ValueError: sharded is not supported for AutoModel ERROR

8

#68 opened over 1 year ago by

peyers

ValueError in KoboldAI when loading the model

#66 opened over 1 year ago by

JermemyHaschal

Cannot set "instructions" when invoking inference endpoint

#65 opened over 1 year ago by

aruana

Changes in modelling_RW.py to be able to handle past_key_values for faster model generations

#64 opened over 1 year ago by

puru22

Model sometimes generates '</s>'

#63 opened over 1 year ago by

jlzhou

Correct blogpost link

#62 opened over 1 year ago by

isydmr

Error: ShardCannotStart

#61 opened over 1 year ago by

Bhupesh2003

Finetuning Falcon-40B-Instruct For ChatBot Use Case

#59 opened over 1 year ago by

sdkramer10

Adding `safetensors` variant of this model

#58 opened over 1 year ago by

nth-attempt

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

#57 opened over 1 year ago by

chiragjn

Adding `safetensors` variant of this model

#56 opened over 1 year ago by

shayan

ValueError: Error raised by inference API: Model tiiuae/falcon-40b-instruct time out using HuggingFaceHub

#55 opened over 1 year ago by

nicoleds

Question about Apache 2.0 license

#54 opened over 1 year ago by

psinger

Running the Falcon-40B-Instruct model on Azure Kubernetes Service

#53 opened over 1 year ago by

zioproto

Experimental ggml demos

#52 opened over 1 year ago by

matthoffner

Truncated output from API call through langchain

4

#51 opened over 1 year ago by

TMTechnology

Experiences with complex instructions

#50 opened over 1 year ago by

Tuana

Update README.md

#49 opened over 1 year ago by

saattrupdan

Why Rotary Positional Embeddings Over Alibi?

#48 opened over 1 year ago by

mallorbc

About Input validation error: `inputs` tokens + `max_new_tokens` must be <= 1512.

#47 opened over 1 year ago by

Holynull

is Alibi version available for fine tuning to a large context window?

#46 opened over 1 year ago by

run

Finetune Falcon-4b with large token size.

#44 opened over 1 year ago by

amnasher

Model returns entire input prompt together with output

11

#43 opened over 1 year ago by

andee96

Instruction prompt

#42 opened over 1 year ago by

mazzaqq

Update README.md

#41 opened over 1 year ago by

zagg8705

Arabic Language support

#40 opened over 1 year ago by

Hgdawy

Request: DOI

#39 opened over 1 year ago by

ongkn

what is the input token length of Falcon-40B and -7B models?

#38 opened over 1 year ago by

sermolin

AttributeError: 'RWConfig' object has no attribute 'n_hea'

#36 opened over 1 year ago by

ibrim

cuda error on more than 400 words

#35 opened over 1 year ago by

a749734

test case one