Daria Soboleva

daria-soboleva's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in cerebras/btlm-3b-8k-base over 1 year ago

Do we have a plan on posting the evaluation results to `open_llm_leaderboard`

3

#26 opened over 1 year ago by

mpsk

New activity in cerebras/btlm-3b-8k-base almost 2 years ago

Context length schedule and performance

3

#25 opened almost 2 years ago by

baffo32

New activity in cerebras/SlimPajama-627B almost 2 years ago

Trouble with streaming

7

#5 opened almost 2 years ago by

andersonbcdefg

Is the data randomly shuffled?

👍 3

2

#4 opened almost 2 years ago by

lmzheng

New activity in cerebras/btlm-3b-8k-base almost 2 years ago

No Cuda Information / nvidia-smi / nvtop

1

#17 opened almost 2 years ago by

nudelbrot

How to reproduce quantized memory usage?

6

#16 opened almost 2 years ago by

tarasglek

Fine-tuning on coding tasks

1

#14 opened almost 2 years ago by

sgaseretto

why we can not make this fully HF ready?

8

#11 opened almost 2 years ago by

CUIGuy

Recommendations for additional pretraining?

4

#8 opened almost 2 years ago by

ZQ-Dev

daria-dev

#1 opened almost 2 years ago by

daria-soboleva

New activity in open-llm-leaderboard/open_llm_leaderboard about 2 years ago

GPT-4 Eval Numbers (How is it known that TruthfulQA used MC2?)

2

#52 opened about 2 years ago by

leoapolonio

New activity in cerebras/SlimPajama-627B about 2 years ago

Running seems to be trapped in a dead cycle

3

#1 opened about 2 years ago by

pathfinder996

New activity in cerebras/Cerebras-GPT-6.7B about 2 years ago

New checkpoint - what's the difference?

2

#1 opened about 2 years ago by

eugeneware