EleutherAI
/

gpt-j-6b

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (16)

Request: DOI

#43 opened about 1 month ago by

gpt-j for thread detectioon

#41 opened 8 months ago by

Adding `safetensors` variant of this model

#40 opened 9 months ago by

[AUTOMATED] Model Memory Requirements

#39 opened 9 months ago by

model-sizer-bot

Adding Evaluation Results

#38 opened about 1 year ago by

leaderboard-pr-bot

Best Way to Load a Model After Training w/o Requantizing

#37 opened over 1 year ago by

Update README.md

#36 opened over 1 year ago by

Error import transformers.models.gptj_modelling-gptj

#35 opened over 1 year ago by

text to sql

#34 opened over 1 year ago by

GPTJForCausalLM LM head weights not initialized?

#33 opened over 1 year ago by

How to get Sentence embeddings?

#32 opened over 1 year ago by

Whats the difference between GPT-J and Pythia?

#31 opened over 1 year ago by

Deployment and infrastructure requirement for GPT-J

#29 opened over 1 year ago by

file input format

#27 opened over 1 year ago by

ValueError: Attempting to unscale FP16 gradients.

#26 opened over 1 year ago by

Tokenizer for GPT-J-6B fails when trying to fine-tune for GLUE tasks

#24 opened over 1 year ago by

Tokenizer loading issue

#23 opened over 1 year ago by

try1

#21 opened over 1 year ago by

Is there a float16 version?

#20 opened over 1 year ago by

RuntimeError: expected scalar type Half but found Float

#19 opened over 1 year ago by

Can this model be used for the Generative Question Answering?

#18 opened almost 2 years ago by

Update config.json

#17 opened almost 2 years ago by

How do you download the whole pack of files?

#16 opened almost 2 years ago by

How to fine tune or train with our own data?

#15 opened almost 2 years ago by

How can we add ability remember the conversation ??

#14 opened almost 2 years ago by

Telegram Info Bot

#13 opened almost 2 years ago by

GPTJForCausalLM hogs memory - inference only

#9 opened about 2 years ago by