YukangChen

Yukang's activity

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

commented a paper 6 months ago

Scaling RL to Long Videos

Paper • 2507.07966 • Published Jul 10 • 159 •

4

New activity in Yukang/LongAlpaca-13B-16k almost 2 years ago

Full FT

1

#1 opened almost 2 years ago by

Nexesenex

New activity in Yukang/LongAlpaca-70B-16k about 2 years ago

Thank you

2

#1 opened about 2 years ago by

MB7977

New activity in Yukang/LongAlpaca-13B about 2 years ago

Testing notes and Recommendations

8

#1 opened about 2 years ago by

RonanMcGovern

New activity in Yukang/Llama-2-13b-longlora-64k about 2 years ago

Can't load any longlora model with Transformers package.

3

#2 opened about 2 years ago by

Julian-CF

New activity in Yukang/LongAlpaca-12k about 2 years ago

Notifications from parquet-converter

6

#1 opened about 2 years ago by

parquet-converter

New activity in Yukang/Llama-2-13b-chat-longlora-32k-sft about 2 years ago

The model produces nonsense

9

#4 opened about 2 years ago by

Pkoosha

New activity in Yukang/Llama-2-70b-chat-longlora-32k-sft about 2 years ago

Is the LongQA dataset is availble

2

#1 opened over 2 years ago by

rajdeep123

New activity in Yukang/Llama-2-13b-chat-longlora-32k-sft about 2 years ago

Evaluation of long sequence of conversation

5

#1 opened over 2 years ago by

cooee-ashutosh

Rope Scaling factor

1

#5 opened about 2 years ago by

jg-ipcopilot

The model seems not have a general ability

6

#3 opened about 2 years ago by

yuansiwe

New activity in Yukang/Llama-2-13b-longlora-64k about 2 years ago

It looks like the model bins were deleted?

1

#1 opened about 2 years ago by

matt-psaltis-devbricks

New activity in Yukang/Llama-2-7b-longlora-100k-ft about 2 years ago

Is this a float32 model?

2

#2 opened about 2 years ago by

RonanMcGovern

New activity in Yukang/Llama-2-13b-chat-longlora-32k-sft over 2 years ago

Why this model kept generating \n when loaded with text generation web ui?

4

#2 opened over 2 years ago by

fahadh4ilyas

New activity in Yukang/Llama-2-70b-chat-longlora-32k-sft over 2 years ago

I am unable to directly load this model?

1

#2 opened over 2 years ago by

hrituraj

New activity in Yukang/Llama-2-13b-longlora-16k over 2 years ago

Yukang/Llama-2-13b-longlora-16k does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.

2

#1 opened over 2 years ago by

GBaker

New activity in Yukang/Llama-2-70b-longlora-32k over 2 years ago

Training VRAM for 70B 32K

1

#1 opened over 2 years ago by

grimulkan

New activity in Yukang/Llama-2-13b-chat-longlora-32k-sft over 2 years ago

Evaluation of long sequence of conversation

5

#1 opened over 2 years ago by

cooee-ashutosh