Hugging Face's logo

berkeley-nest
/
Starling-LM-7B-alpha

Text Generation
Transformers
Safetensors
English
mistral
reward model
RLHF
RLAIF
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
32
New discussion

limits?
#32 opened 6 months ago by tcporco

Adding Evaluation Results
#31 opened 8 months ago by leaderboard-pr-bot

Why change the licence ?

1
#30 opened 9 months ago by trashpanda75

Responsible for me

1
#28 opened 10 months ago by Anonimus12345678902

Beta or V2 release?

3
#27 opened 10 months ago by rjmehta

Issues in the tokenizer

4
#25 opened 10 months ago by Imran1

Hyperparameters?

1
#23 opened 11 months ago by ekurtulus

What could be instruction fine tuning prompt for this model?

5
#22 opened 11 months ago by andreaKIM

extremely variable response time for inference?

9
#21 opened 11 months ago by silvacarl

Cant wait for Beta Version

5
#19 opened 11 months ago by rjmehta

Won't stop spitting training data

6
#18 opened 11 months ago by topastop

Fine tuning with transformers?

3
#17 opened 11 months ago by toranb

can't autotune
#16 opened 11 months ago by legolasyiu

Can use chatml format?

1
#15 opened 12 months ago by lucasjin

Maybe you could try on Yi-34B

1
#12 opened 12 months ago by Yhyu13

The Model move betwwen languages

1
#9 opened 12 months ago by eramax

best model params

11
#8 opened 12 months ago by eramax

Pytorch format available?

3
#7 opened 12 months ago by vmajor

Paragraph Breaks

3
#4 opened 12 months ago by Shasho423

Surprisingly impressive!

1
#1 opened 12 months ago by Cypherfox