tiiuae
/

falcon-40b

Text Generation

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (40)

Keep getting 'model_kwargs` are not used by the model: ['token_type_ids']

#60 opened about 1 year ago by

Falcon models slow inference

#59 opened about 1 year ago by

I need an API of Falcon

#56 opened about 1 year ago by

Google Colab for Falcon 40B and 7B with Live Response Streaming

#55 opened about 1 year ago by

can anyone help me get prompt template for Question Answering model

#54 opened about 1 year ago by

Iamexperimenting

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

Batch inference seems to be done sequentially

#50 opened about 1 year ago by

Extracting attention maps

#49 opened about 1 year ago by

Error with custom inference loop with past_key_values

#48 opened about 1 year ago by

Fix the kv-cache dimensions

#47 opened about 1 year ago by

Multi GPU inference issue

#39 opened over 1 year ago by

Is it on purpose? loss for singlelable and multilable switched.

#36 opened over 1 year ago by

Fine-tuning on a new language

#35 opened over 1 year ago by

Flash attention

#34 opened over 1 year ago by

about evaluating on humaneval

#33 opened over 1 year ago by

Finetune on "uncensored" dataset?

#32 opened over 1 year ago by

Tokenizer Details

#31 opened over 1 year ago by

kye

Import dataset and chat with it

#27 opened over 1 year ago by

Working code with full server requirements

#24 opened over 1 year ago by

Bug: Generate method doesn't work for falcon-7b and falcon-40b in int8 mode.

#22 opened over 1 year ago by

It can run with two 4090 or a single 6000 ADA.

#20 opened over 1 year ago by

请求：DOI

#16 opened over 1 year ago by

Finetune wtih QLoRA please

#14 opened over 1 year ago by

How to set trust_remote_code to true?

#9 opened over 1 year ago by

[Bug] Does not work

#3 opened over 1 year ago by