Weiguo Liao

Weiguo's activity

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

liked a Space 11 days ago

Running on T4

20

🌖

Omni Mini (WebRTC)

New activity in freddyaboulton/omni-mini-webrtc 11 days ago

how to change whisper small to large?

#2 opened 11 days ago by Weiguo

New activity in Qwen/Qwen-7B-Chat over 1 year ago

我看模型更新了，有说明吗

2

#21 opened over 1 year ago by Weiguo

ReAct目前支持吗，有人做过没有

2

#16 opened over 1 year ago by Weiguo

Add support for flash-attention2

2

#3 opened over 1 year ago by wunein

有没有人写一个stream_chat，现在的体验有点差

11

#6 opened over 1 year ago by Weiguo

貌似很拉跨，一个7B的模型3090显存都不够载入，要是不安装它推荐的加速包，速度慢的像狗。

15

#12 opened over 1 year ago by boxter007

BF16是不是依赖CUDA 11.7，我的机器是12.2

3

#7 opened over 1 year ago by Weiguo

New activity in LinkSoul/Chinese-Llama-2-7b over 1 year ago

试了一下效果不错，有没有更大参数版本放出来

2

#9 opened over 1 year ago by Weiguo

速度非常慢，非常非常慢

1

#3 opened over 1 year ago by Weiguo

liked 2 models over 1 year ago

TheBloke/Llama-2-13B-GGML

Text Generation • Updated Sep 27, 2023 • 47 • 175

moka-ai/m3e-base

Updated Jul 14, 2023 • 278k • 899

New activity in michaelwzhu/ShenNong-TCM-LLM over 1 year ago

entity_centric_self_instruct.py 不存在

1

#1 opened over 1 year ago by Weiguo

liked a Space over 1 year ago

Sleeping

225

🐠

FastSAM

New activity in bigcode/starcoder over 1 year ago

How big RAM do we need to deploy this module

1

#39 opened over 1 year ago by Weiguo

liked a model over 1 year ago

bigcode/starcoder

Text Generation • Updated Oct 8 • 13.6k • • 2.81k