tiiuae/falcon-40b · Discussions

Falcon 40B Inference at 4bit in Google Colab

pinned

27

#38 opened 11 months ago by

serin32

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

pinned

6

#25 opened 11 months ago by

rmihaylov

Could not locate the configuration_RW.py inside tiiuae/falcon-40b-instruct.

#114 opened 10 days ago by

cosmino

[AUTOMATED] Model Memory Requirements

#113 opened 26 days ago by

model-sizer-bot

Adding `safetensors` variant of this model

#112 opened about 1 month ago by

SFconvertbot

Adding Evaluation Results

#111 opened 2 months ago by

leaderboard-pr-bot

Could someone upload a tokenizer.model file? to allow for making ggufs

#110 opened 6 months ago by

RonanMcGovern

Add chat_template so that it can be used for chat out-of-box

#109 opened 6 months ago by

chujiezheng

pb when testing the model

#108 opened 7 months ago by

louvivien

Update generation_config.json

1

#106 opened 8 months ago by

nkasmanoff

Gradio interface

#105 opened 8 months ago by

sequentialsystems

Optimizing Inference Time for Chat Conversations on Falcon

2

#104 opened 9 months ago by

humza-sami

Finetuned Falcon40 is not working with pipeline (text-generation)

#103 opened 9 months ago by

chelouche9

Advice on inference over a large-ish dataset in Databricks?

#102 opened 9 months ago by

archonlith

Use input attention mask instead of casual mask in attention

#101 opened 9 months ago by

CyberZHG

Inference

4

#99 opened 9 months ago by

davidhung

Best Practice for Handling Variable-Length Sequences in Training an LLM Model on a Chatbot Dataset

#98 opened 9 months ago by

humza-sami

Request: DOI

#97 opened 10 months ago by

waelTalan

Getting HTTP Error Code: 422 when using Inference API

2

#96 opened 10 months ago by

reetkat

Run falcon on Mac

2

#95 opened 10 months ago by

corin9122

Unable to use all cores.

2

#94 opened 10 months ago by

armx40

Bug: the model's head dimensionality is hardcoded

#93 opened 10 months ago by

danieldk-explosion

Fine-tune on model response only?

1

#92 opened 10 months ago by

mkserge

Finetuning Base Falcon on Unseen Language/New data (non instruct/RLHF)

2

#91 opened 10 months ago by

AshBam

Slow response time for 7b and 40b

6

#89 opened 10 months ago by

kartik99

configuration_RW.py Missing in the latest commit

#88 opened 10 months ago by

ravikiran3690

Update README.md

2

#87 opened 10 months ago by

FelixMildon

Falcon breaks after the second prompt of code.

#86 opened 10 months ago by

thecowmilk

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

8

#85 opened 10 months ago by

puru22

@TII Falcon is stunning but will you continue or is the majestic bird destined to starve ?

#84 opened 10 months ago by

cmp-nct

Finetune Error using the notebook referred on the model page

#83 opened 10 months ago by

hamad

Nvidia H100 Finetuning Error on BitsandBytes

2

#82 opened 10 months ago by

ashmitbhattarai

new here, confused which .bin file to download?

#80 opened 10 months ago by

kingofdelphi

Update generation_config.json

#77 opened 10 months ago by

psinger

Request: DOI

#76 opened 10 months ago by

winter6below618

Seeking insights on integrating RAG with Falcon for Domain Specific requirements

#75 opened 10 months ago by

rahul2008d

Prevent Hallucinations

1

#74 opened 10 months ago by

Zhaoqiong

Deployment on Azure ML

1

#73 opened 10 months ago by

Eliahu551818

Access To Hidden States

#72 opened 10 months ago by

DJT777

Were special tokens trained?

#71 opened 10 months ago by

Tron2060

Example code from README output is nonsense

1

#70 opened 10 months ago by

amitgurintecom

New language

2

#69 opened 11 months ago by

mindplay

GPU requirements

7

#68 opened 11 months ago by

GuySerk

Cuda out of memory error.

2

#67 opened 11 months ago by

ibrim

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)

1

#66 opened 11 months ago by

yiz4869

How to fine tune falcon for summarization on xsum?

1

#65 opened 11 months ago by

uzumakiusa

Need claritiy about the adjustable model hyperparameters

#64 opened 11 months ago by

Someshfengde

Update README.md

#63 opened 11 months ago by

Gage888

Borken docs link Use in transformers

1

#62 opened 11 months ago by

natika1

Hello, may I know where can I get the embeddings for falcon-40b?

3

#61 opened 11 months ago by

kurtgan