Haoxiang Wang

Haoxiang-Wang's activity

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

New activity in nvidia/Cosmos-1.0-Autoregressive-4B 4 months ago

access restriction

1

#3 opened 4 months ago by

qyx915915

Access restrictions

#2 opened 4 months ago by

fximax

New activity in nvidia/Cosmos-0.1-Tokenizer-DV8x16x16 6 months ago

Update README.md

#1 opened 6 months ago by

Haoxiang-Wang

New activity in RLHFlow/ArmoRM-Llama3-8B-v0.1 8 months ago

Why is the code-complexity coefficient so high in the demo example?

1

#16 opened 8 months ago by

icdt

Special tokens in the vocabulary?

4

#13 opened 9 months ago by

nshen7

Original reward space

1

#15 opened 8 months ago by

anjaa

New activity in RLHFlow/ArmoRM-Llama3-8B-v0.1 9 months ago

[AUTOMATED] Model Memory Requirements

#5 opened 10 months ago by

model-sizer-bot

What is the range of the output score from the model?

2

#12 opened 9 months ago by

nshen7

Why is `multi_obj_rewards` multipled by 5, but then 0.5 is subtracted from it?

2

#11 opened 9 months ago by

xzuyn

Update README.md

1

#3 opened 11 months ago by

philschmid

Issue when finetuning the reward model on custom dataset

1

#2 opened 11 months ago by

yguooo

Longer context

1

#10 opened 9 months ago by

salazaaar

New activity in RLHFlow/ArmoRM-Llama3-8B-v0.1 10 months ago

batched predictions with padding through the model don't seem to work correctly

5

#7 opened 10 months ago by

karthikramen

ModuleNotFoundError: No module named 'transformers_modules.RLHFlow.ArmoRM-Llama3-8B-v0'

1

#6 opened 10 months ago by

fchaubard

Why Not Utilize a Sigmoid Function in the Regression Layer?

1

#8 opened 10 months ago by

xwz-xmu

New activity in allenai/reward-bench 11 months ago

Separate Scores: With & Without Prior Sets

3

#6 opened 11 months ago by

Haoxiang-Wang

New activity in RLHFlow/ArmoRM-Llama3-8B-v0.1 11 months ago

Problem running the model

2

#1 opened 11 months ago by

Asaf-Yehudai

New activity in RLHFlow/LLaMA3-iterative-DPO-final 11 months ago

exl2 quants

1

#2 opened 11 months ago by

Apel-sin

New activity in RLHFlow/pair-preference-model-LLaMA3-8B 11 months ago

CAn you specify the license for this model please ?

1

#1 opened 11 months ago by

sparsh35

commented a paper 12 months ago

RLHF Workflow: From Reward Modeling to Online RLHF

Paper • 2405.07863 • Published May 13, 2024 • 71 •

5