Introducing HuggingFace blog for Chinese speakers: Fostering Collaboration with the Chinese AI community
ā¢
2
Tiezhen WANG
xianbao
AI & ML interests
This
is
my
personal
account
Articles
Organizations
Posts
6
Post
1281
Why Apache 2.0 Matters for LLMs š¤
@01AI_Yi recently switched from a permissive & commercially friendly license, to Apache 2.0. And the community loved it! š
@JustinLin610 also had a poll on model license and the majority votes for Apache 2.0.
Why it is a Big Deal? ā¬ļø
š Legal Simplicity: Custom licenses need costly & time-consuming legal review. Apache 2.0 is well-known & easier for legal teams to handle.
š©āš» Developer-Friendly: Legal docs are a pain for devs! Apache 2.0 is well-known and tech-friendly, making it easier for non-native developers to understand the implications too.
š Easier Integration: Apache 2.0 is compatible with many other licenses, simplifying tasks like model merging with models of different licensing requirements.
š« No Permission Needed: Custom licenses often require explicit permission and additional documentation work of filling forms, creating barriers. Apache 2.0 removes this hurdle, letting devs focus on innovation.
There are a lot interesting discussions from
@JustinLin610 's poll: https://x.com/JustinLin610/status/1793559737482764375 which inspired this thread.
Any other thoughts? Let me know ^^
@01AI_Yi recently switched from a permissive & commercially friendly license, to Apache 2.0. And the community loved it! š
@JustinLin610 also had a poll on model license and the majority votes for Apache 2.0.
Why it is a Big Deal? ā¬ļø
š Legal Simplicity: Custom licenses need costly & time-consuming legal review. Apache 2.0 is well-known & easier for legal teams to handle.
š©āš» Developer-Friendly: Legal docs are a pain for devs! Apache 2.0 is well-known and tech-friendly, making it easier for non-native developers to understand the implications too.
š Easier Integration: Apache 2.0 is compatible with many other licenses, simplifying tasks like model merging with models of different licensing requirements.
š« No Permission Needed: Custom licenses often require explicit permission and additional documentation work of filling forms, creating barriers. Apache 2.0 removes this hurdle, letting devs focus on innovation.
There are a lot interesting discussions from
@JustinLin610 's poll: https://x.com/JustinLin610/status/1793559737482764375 which inspired this thread.
Any other thoughts? Let me know ^^
Post
1064
DeepSeekV2 is a big deal. Not only because its significant improvements to both key components of Transformer: the Attention layer and FFN layer.
It has also completed disrupted the Chines LLM market and forcing the competitors to drop the price to 1% of the original price.
---
There are two key components in Transformer architecture: the self-attention layer, which captures relationships between tokens in context, and the Feed-Forward Network (FFN) layer, which stores knowledge.
DeepSeek V2 introduces optimizations to both:
Attention layer normally uses KV Cache to reduce repetitive compute, but it consumes significant GPU RAM, limiting concurrent requests. DeepSeek V2 introduces Multi-head Latent Attention (MLA), which stores only a small latent representation, resulting in substantial RAM savings.
DeepSeek V2 utilizes 162 experts instead of the usual 8 as in Mixtral. This approach segments experts into finer granularity for higher specialization and more accurate knowledge acquisition. Activating only a small subset of experts for each token, leads to efficient processing.
It disrupted the market by dropping API prices to $0.14 per 1M tokens. This dramatic reduction forced competitors like GLM, Ernie, and QWen to follow suit, lowering their prices to 1% of their original offerings. Now, users can access these APIs at 1/35th the cost of ChatGPT-4o.
It has also completed disrupted the Chines LLM market and forcing the competitors to drop the price to 1% of the original price.
---
There are two key components in Transformer architecture: the self-attention layer, which captures relationships between tokens in context, and the Feed-Forward Network (FFN) layer, which stores knowledge.
DeepSeek V2 introduces optimizations to both:
Attention layer normally uses KV Cache to reduce repetitive compute, but it consumes significant GPU RAM, limiting concurrent requests. DeepSeek V2 introduces Multi-head Latent Attention (MLA), which stores only a small latent representation, resulting in substantial RAM savings.
DeepSeek V2 utilizes 162 experts instead of the usual 8 as in Mixtral. This approach segments experts into finer granularity for higher specialization and more accurate knowledge acquisition. Activating only a small subset of experts for each token, leads to efficient processing.
It disrupted the market by dropping API prices to $0.14 per 1M tokens. This dramatic reduction forced competitors like GLM, Ernie, and QWen to follow suit, lowering their prices to 1% of their original offerings. Now, users can access these APIs at 1/35th the cost of ChatGPT-4o.
Collections
2
Portfolio of LLAMA3 fine-tune models
-
UnicomLLM/Unichat-llama3-Chinese-8B
Text Generation ā¢ Updated ā¢ 1.7k ā¢ 71 -
shareAI/llama3-Chinese-chat-8b
Question Answering ā¢ Updated ā¢ 41 -
OpenBuddy/openbuddy-llama3-8b-v21.1-8k
Text Generation ā¢ Updated ā¢ 2.61k ā¢ 29 -
BoyangZ/llama3_chinese_basemode_ftv1
Text Generation ā¢ Updated ā¢ 2 ā¢ 2
Papers
1
spaces
25
models
19
xianbao/test-private-glm
Updated
xianbao/mediapipe-gemma-2b-it
Updated
ā¢
1
xianbao/test-model
Updated
xianbao/test-wiki
Updated
xianbao/tetes-test
Updated
xianbao/demo_test
Text-to-Image
ā¢
Updated
xianbao/test-target
Fill-Mask
ā¢
Updated
xianbao/test-upload
Updated
xianbao/dashdash-toy
Text-to-Image
ā¢
Updated
ā¢
1
ā¢
3
xianbao/dashdash-toy-heywhale-3
Text-to-Image
ā¢
Updated
ā¢
1
ā¢
2