Alexander Borzunov

borzunov's activity

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

New activity in garage-bAInd/Platypus2-70B-instruct 8 months ago

Why do you set `use_cache=False`? Removing it will speed up generation

1

#8 opened 8 months ago by borzunov

New activity in codellama/CodeLlama-34b-Instruct-hf 8 months ago

Model pads response with newlines up to max_length

2

#6 opened 8 months ago by borzunov

New activity in Maykeye/TinyLLama-v0 9 months ago

Thank you for creating this model!

1

#2 opened 9 months ago by borzunov

New activity in tiiuae/falcon-40b 10 months ago

Revert in-library PR

3

#90 opened 10 months ago by Rocketknight1

New activity in timdettmers/guanaco-65b 10 months ago

Add safetensor version

2

#3 opened 10 months ago by artek0chumak

New activity in bigscience/bloomz about 1 year ago

A way to inference and fine-tune BLOOMZ-176B from Google Colab or locally

2

#28 opened over 1 year ago by borzunov

New activity in bigscience/bloom over 1 year ago

Fine-tune the model?

82

#46 opened almost 2 years ago by NXBY

A way to inference and fine-tune BLOOM-176B from Google Colab or locally

2

#152 opened over 1 year ago by borzunov

What does it take to self-host Bloom? How much money would that cost?

7

#161 opened over 1 year ago by damc

Eats up all RAM + 163GB Swap

4

#167 opened over 1 year ago by LuvIsBadToTheBone

New activity in bigscience/bloomz over 1 year ago

No longer available, why?

11

#21 opened over 1 year ago by micole66

New activity in bigscience/bloom-petals over 1 year ago

Update README.md

#2 opened over 1 year ago by borzunov

New activity in hivemind/gpt-j-6B-8bit over 1 year ago

hivemind / gpt-j-6B-8bit , How can i use Multiple GPU , I treid using accelerate and also using torch.nn.dataparallel() nothing works out

1

#11 opened over 1 year ago by MukeshSharma

New activity in CALM/arwiki almost 2 years ago

Fix `license` metadata

#1 opened almost 2 years ago by julien-c