Making sense of this mess
โข
14
Steven Liu
stevhliu
AI & ML interests
None yet
Recent Activity
New activity
26 days ago
huggingface/documentation-images:cogvideox-images diffusers/pull/9578
Articles
Organizations
stevhliu's activity
cogvideox-images diffusers/pull/9578
2
#371 opened about 2 months ago
by
dmeck
dmeck
updated
a
dataset
2 months ago
liked
a
model
2 months ago
updated
a
Space
3 months ago
liked
a
model
3 months ago
liked
a
model
4 months ago
upvoted
a
paper
4 months ago
update org card
6
#3 opened 4 months ago
by
stevhliu
stevhliu
liked
a
model
4 months ago
Update images for Argilla cookbooks
#23 opened 4 months ago
by
sdiazlor
sdiazlor
updated
a
dataset
4 months ago
Add images for "Information Extraction with Haystack and NuExtract" notebook
#22 opened 4 months ago
by
anakin87
anakin87
Upload colab-secrets.jpeg
#20 opened 5 months ago
by
lloydmeta
lloydmeta
updated
3
Spaces
6 months ago
Reacted to
m-ric's
post with ๐
6 months ago
Post
1038
๐๐๐ฐ ๐ ๐ฎ๐ข๐๐ ๐ข๐ง ๐จ๐ฎ๐ซ ๐๐ฉ๐๐ง-๐๐จ๐ฎ๐ซ๐๐ ๐๐ ๐๐จ๐จ๐ค๐๐จ๐จ๐ค: ๐๐ฉ๐ง๐ช๐๐ฉ๐ช๐ง๐๐ ๐๐๐ฃ๐๐ง๐๐ฉ๐๐ค๐ฃ! โจ
Many use LLM use cases involve generating outputs with a specific structure.
โก๏ธ For instance when using an LLM as a judge to evaluate another model's outputs, you need it to give you not only a score, but also the rationale for this score, and maybe a confidence level.
So you do not need only "score: 1", but more a dictionary like:
๐ค How to force your LLM to generate such a structured output?
๐๏ธ ๐๐ผ๐ป๐๐๐ฟ๐ฎ๐ถ๐ป๐ฒ๐ฑ ๐ฑ๐ฒ๐ฐ๐ผ๐ฑ๐ถ๐ป๐ด is a great technique to generate structured output: you can specify a grammar (=set of rules) that the output should follow, and ๐ฐ๐ผ๐ป๐๐๐ฟ๐ฎ๐ถ๐ป๐ฒ๐ฑ ๐ฑ๐ฒ๐ฐ๐ผ๐ฑ๐ถ๐ป๐ด ๐๐ต๐ฒ๐ป ๐ณ๐ผ๐ฟ๐ฐ๐ฒ๐ ๐๐ต๐ฒ ๐ฑ๐ฒ๐ฐ๐ผ๐ฑ๐ฒ๐ฟ ๐๐ผ ๐ผ๐ป๐น๐ ๐ฝ๐ถ๐ฐ๐ธ ๐๐ผ๐ธ๐ฒ๐ป๐ ๐๐ต๐ฎ๐ ๐ฟ๐ฒ๐๐ฝ๐ฒ๐ฐ๐ ๐๐ผ๐๐ฟ ๐ด๐ฟ๐ฎ๐บ๐บ๐ฎ๐ฟ.
I've created a guide to show you how to use it, both via our Inference API and locally using ๐ฐ๐ถ๐ต๐ญ๐ช๐ฏ๐ฆ๐ด!
๐ Read it here: https://huggingface.co/learn/cookbook/structured_generation
Thank you @stevhliu for your great help in improving it!
Many use LLM use cases involve generating outputs with a specific structure.
โก๏ธ For instance when using an LLM as a judge to evaluate another model's outputs, you need it to give you not only a score, but also the rationale for this score, and maybe a confidence level.
So you do not need only "score: 1", but more a dictionary like:
{
"rationale": "The answer does not match the true answer at all."
"score": 1,
"confidence_level": 0.85
}๐ค How to force your LLM to generate such a structured output?
๐๏ธ ๐๐ผ๐ป๐๐๐ฟ๐ฎ๐ถ๐ป๐ฒ๐ฑ ๐ฑ๐ฒ๐ฐ๐ผ๐ฑ๐ถ๐ป๐ด is a great technique to generate structured output: you can specify a grammar (=set of rules) that the output should follow, and ๐ฐ๐ผ๐ป๐๐๐ฟ๐ฎ๐ถ๐ป๐ฒ๐ฑ ๐ฑ๐ฒ๐ฐ๐ผ๐ฑ๐ถ๐ป๐ด ๐๐ต๐ฒ๐ป ๐ณ๐ผ๐ฟ๐ฐ๐ฒ๐ ๐๐ต๐ฒ ๐ฑ๐ฒ๐ฐ๐ผ๐ฑ๐ฒ๐ฟ ๐๐ผ ๐ผ๐ป๐น๐ ๐ฝ๐ถ๐ฐ๐ธ ๐๐ผ๐ธ๐ฒ๐ป๐ ๐๐ต๐ฎ๐ ๐ฟ๐ฒ๐๐ฝ๐ฒ๐ฐ๐ ๐๐ผ๐๐ฟ ๐ด๐ฟ๐ฎ๐บ๐บ๐ฎ๐ฟ.
I've created a guide to show you how to use it, both via our Inference API and locally using ๐ฐ๐ถ๐ต๐ญ๐ช๐ฏ๐ฆ๐ด!
๐ Read it here: https://huggingface.co/learn/cookbook/structured_generation
Thank you @stevhliu for your great help in improving it!
updated
a
dataset
6 months ago
updated
a
model
7 months ago
liked
a
Space
7 months ago