Jonas Geiping

JonasGeiping's activity

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

New activity in tomg-group-umd/huginn-0125 17 days ago

Supervised fine-tuning and dpo implementation

1

#11 opened 23 days ago by

Vitabile

New activity in tomg-group-umd/huginn-0125 25 days ago

Issues faced in reproducing the paper's experiments

7

#8 opened 3 months ago by

Chensmile

New activity in tomg-group-umd/huginn-dataset about 1 month ago

[bot] Conversion to Parquet

#1 opened 2 months ago by

parquet-converter

New activity in tomg-group-umd/pez-dispenser about 2 months ago

Runtime Error

2

#7 opened 2 months ago by

Marseve

New activity in tomg-group-umd/huginn-0125 2 months ago

Fine-tuning Model

3

#9 opened 3 months ago by

MrWheels523

Could you describe in simple words how it really works?

1

5

#3 opened 3 months ago by

MarcinCF

Can we quantize the model to GGUF or GPTQ?

1

#10 opened 2 months ago by

MLDataScientist

Confusion in the model architecture

3

#4 opened 3 months ago by

Ink

New activity in tomg-group-umd/huginn-0125 3 months ago

Confusion about the description of evaluation settings

7

#7 opened 3 months ago by

CrazyD

Add link to code and project page

3

#6 opened 3 months ago by

nielsr

Parallelization support

1

#5 opened 3 months ago by

yigitbekir

commented a paper 3 months ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 140 •

12

New activity in tomg-group-umd/huginn-0125 3 months ago

Update README.md

1

#2 opened 3 months ago by

gghfez

commented 3 papers 3 months ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 140 •

12

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 140 •

12

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 140 •

12

New activity in wikimedia/wikipedia 9 months ago

How to improve the wikimedia/wikipedia dataset

5

#63 opened 11 months ago by

albertvillanova

New activity in JonasGeiping/the_pile_WordPiecex32768_53b28db05413b6497e702f178268e1e2 about 1 year ago

[bot] Conversion to Parquet

#1 opened about 1 year ago by

parquet-converter

commented a paper about 1 year ago

Coercing LLMs to do and reveal (almost) anything

Paper • 2402.14020 • Published Feb 21, 2024 • 13 •

2

New activity in JonasGeiping/crammed-bert-legacy over 1 year ago

Adding `safetensors` variant of this model

1

#1 opened over 1 year ago by

SFconvertbot