Custom generation methods
Collection
Custom generation methods that are maintained by the `transformers` team.
β’
3 items
β’
Updated
β’
2
Transformers Community
AI & ML interests
None defined yet.
Recent Activity
transformers-community's activity
joaoganteΒ
updated
a
collection
10 days ago
joaoganteΒ
updated
a
model
10 days ago
joaoganteΒ
published
a
model
14 days ago
Post
450
Let's go! Custom generation code has landed in
Have you designed a new cool KV cache? Maybe you're comparing new test-time compute ideas you've been researching? Have you found a way to do diffusion with existing models? You can now easily share your findings with the community with custom generation code, sharing the well-known
In a nutshell, we have expanded the support of custom modeling code on the Hub with *model-agnostic* custom generation code. Write for one model, reuse with any model -- hopefully, this will democratize access to new generation ideas π«‘
As a creator, you gain the ability to get your ideas in
π Resources π
- docs: https://huggingface.co/docs/transformers/generation_strategies#custom-decoding-methods
- minimal example: transformers-community/custom_generate_example
- discussion: transformers-community/support#10
transformers πHave you designed a new cool KV cache? Maybe you're comparing new test-time compute ideas you've been researching? Have you found a way to do diffusion with existing models? You can now easily share your findings with the community with custom generation code, sharing the well-known
generate interface π€In a nutshell, we have expanded the support of custom modeling code on the Hub with *model-agnostic* custom generation code. Write for one model, reuse with any model -- hopefully, this will democratize access to new generation ideas π«‘
As a creator, you gain the ability to get your ideas in
transformers with minimal effort. You'll also have access to all Hub features: a landing page for your creation, discussions, usage metrics, ... π€π Resources π
- docs: https://huggingface.co/docs/transformers/generation_strategies#custom-decoding-methods
- minimal example: transformers-community/custom_generate_example
- discussion: transformers-community/support#10
Custom `generate` methods discussion
π
π₯
3
#10 opened 17 days ago
by
joaogante
Post
3644
hey hey
@mradermacher
- VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! π₯
as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!
in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.
p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage
p.p.s. this is fully backwards compatible so everything will work as it should! π€
as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!
in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.
p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage
p.p.s. this is fully backwards compatible so everything will work as it should! π€
- 16 replies
The Transformers Library: standardizing model definitions
π€
β€οΈ
14
3
#7 opened 21 days ago
by
lysandre
lysandreΒ
updated
a
Space
21 days ago
joaoganteΒ
updated
2
models
23 days ago
joaoganteΒ
updated
a
collection
23 days ago
joaoganteΒ
published
a
model
23 days ago
joaoganteΒ
updated
a
collection
23 days ago
joaoganteΒ
published
a
model
23 days ago
Add releases tab
1
#6 opened 26 days ago
by
lysandre
Add releases tab
1
#6 opened 26 days ago
by
lysandre
Post
3221
FramePack is hands down one of the best OS releases in video generation ππ»ββοΈπ€―
β fully open sourced + amazing quality + reduced memory + improved speed
but more even - its gonna facilitate *soooo* many downstream applications
like this version adapted for landscape rotation πhttps://huggingface.co/spaces/tori29umai/FramePack_rotate_landscape
β fully open sourced + amazing quality + reduced memory + improved speed
but more even - its gonna facilitate *soooo* many downstream applications
like this version adapted for landscape rotation πhttps://huggingface.co/spaces/tori29umai/FramePack_rotate_landscape
- 2 replies
Post
4636
Transformers this, transformers that..
π
1
#4 opened about 1 month ago
by
reach-vb