Hugging Face's logo

OpenAssistant
/
oasst-sft-4-pythia-12b-epoch-3.5

Text Generation
Transformers
PyTorch
English
gpt_neox
sft
text-generation-inference
Inference Endpoints
Model card Files Community
34
New discussion

Interview request: genAI evaluation & documentation
#34 opened about 2 months ago by evatang

Service unavailiable

4
#33 opened 7 months ago by VladSolyankin

Adding `safetensors` variant of this model
#32 opened 8 months ago by SFconvertbot

Adding Evaluation Results
#30 opened 9 months ago by leaderboard-pr-bot

Adding Evaluation Results
#29 opened about 1 year ago by leaderboard-pr-bot

Load in pythia-12b

1
#28 opened about 1 year ago by ghidav

Adding `safetensors` variant of this model
#27 opened about 1 year ago by lixue233

Adding `safetensors` variant of this model
#26 opened about 1 year ago by lixue233

few shot learning

#25 opened about 1 year ago by project-test

Vercel AI SDK

3
#24 opened over 1 year ago by julianouxui

How to load this model in 4bit?
#23 opened over 1 year ago by banank1989

Giving Partial answers

3
#22 opened over 1 year ago by deepakkaura26

URGENT (Can someone help me?)

1
#21 opened over 1 year ago by sancassino

Reproducing the fine tuning gets stuck with 100% CPU on one process
#20 opened over 1 year ago by felipemv

How to reduce batch size in order to solve CUDA out of memory error?

3
#19 opened over 1 year ago by samyar03

Probability tensor contains either `inf`, `nan` or element < 0

1
#18 opened over 1 year ago by rociomcomin

OpenAssistant API

5
#16 opened over 1 year ago by DeeJaye

How can I use Sagemaker's inference recommender for this model for question-answering task?
#15 opened over 1 year ago by monasbhar09

Facing error while inferencing

2
#14 opened over 1 year ago by sauravm8

How to use the special token `<|system|>` effectively?

1
#13 opened over 1 year ago by AayushShah

Can the model be used for commercial purposes?

5
#11 opened over 1 year ago by AayushShah

CUDA out of memory

3
#10 opened over 1 year ago by Blue-Devil

gptneox.cpp - Fork of llama.cpp (ggml) for OpenAssistant usage
#9 opened over 1 year ago by byroneverson

epoch-8 version
#8 opened over 1 year ago by gsaivinay

Slow inference time for new version of transformers

11
#7 opened over 1 year ago by russellsparadox

wandb link does not seem to work

1
#6 opened over 1 year ago by mingaflo

Embeddings?
#5 opened over 1 year ago by hydronab

4bit gglm version?

1
#4 opened over 1 year ago by jbollenbacher

Some Technical and Usage Information
#3 opened over 1 year ago by gsaivinay

How to run that?

23
#2 opened over 1 year ago by Guilherme34

Alpaca in dataset

27
#1 opened over 1 year ago by morganpie