Inference for PROs
β’
8
Victor Mustar PRO
victor
AI & ML interests
AI + User experience
Articles
Organizations
victor's activity
replied to
their
post
36 minutes ago
for others: huggingface.co/chat
yes π
replied to
ehristoforu's
post
5 days ago
I think I get better results without negative prompt but could be wrong π
replied to
ehristoforu's
post
5 days ago
π₯π₯ v3 Lightning at 1536x1536 has great level of detail
Paper page: https://huggingface.co/papers/2404.19756
Super fast! this is awesome!!
posted
an
update
7 days ago
Post
3272
The hype is real: a mysterious gpt2-chatbot model has appeared on the LLM Arena Leaderboard π.
It seems to be at least on par with the top performing models (closed and open).
To try it out: https://chat.lmsys.org/ -> then click on the Direct Chat tab and select gpt2-chatbot.
Take your bet, what do you think it is?
It seems to be at least on par with the top performing models (closed and open).
To try it out: https://chat.lmsys.org/ -> then click on the Direct Chat tab and select gpt2-chatbot.
Take your bet, what do you think it is?
- 4 replies
posted
an
update
7 days ago
Post
1895
Am I the only one who think command-r-+ is a better daily Assistant than ChatGPT-4? (and it's not even close :D)
- 6 replies
posted
an
update
7 days ago
Post
1487
If you are into video generation you should check this great Space by
@KingNish
- generate videos in ~10 seconds!
KingNish/Instant-Video
KingNish/Instant-Video
Looks clean! need a ZeroGPU Spaces to play with it π
Seems quite impressive indeed :)
π₯π₯ (Invited you to ZeroGPU if there's interest π)
Looks super polished π well done!
replied to
HeshamHaroon's
post
13 days ago
You know too much about HF π
replied to
isidentical's
post
13 days ago
At last an Arena where it's quick and fun to rate things! well done π
replied to
HeshamHaroon's
post
14 days ago
π Anyway welcome to Posts!
replied to
theStevenochs's
post
24 days ago
Yes but this is really fun!
replied to
theStevenochs's
post
24 days ago
That looks awesome! need a username/password :D
replied to
mayank-mishra's
post
26 days ago
Great writing!
Awesome! Prompt compression is going to be huge this year!
replied to
their
post
about 2 months ago
This comment has been hidden
replied to
their
post
about 2 months ago
If you want to generate a description for a space, you can use this: https://huggingface.co/spaces/julien-c/description-generator (I stole the prompt)
posted
an
update
about 2 months ago
Post
2192
I just uploaded a Dataset that adds AI descriptions to top trending Spaces! It is really useful to find awesome Spaces π
victor/hf-spaces-with-descriptions
I used HF Serverless Endpoints (with Mixtral) to get the descriptions, it was seamless to do! btw check out the new Serverless Endpoints dashboard - it's awesome!
victor/hf-spaces-with-descriptions
I used HF Serverless Endpoints (with Mixtral) to get the descriptions, it was seamless to do! btw check out the new Serverless Endpoints dashboard - it's awesome!
-
- 2 replies
replied to
their
post
about 2 months ago
posted
an
update
2 months ago
Post
π There's now a visible description on Spaces previews. You can set the description of your Spaces by editing their README.md - it should make your Spaces more discoverable π.
- 1 reply
I don't think it's running locally so it's not similar.
replied to
their
post
3 months ago
lol whatβs the use case?
replied to
their
post
3 months ago
π
replied to
their
post
3 months ago
π
replied to
their
post
3 months ago
π
replied to
their
post
3 months ago
π’
posted
an
update
3 months ago
Post
π Let's try to figure out this one as a community.
What reactions should we add to Posts and discussions?
If the reaction you want is already in the replies give it a thumbs up (π) if it's not just add it as a reply.
What reactions should we add to Posts and discussions?
If the reaction you want is already in the replies give it a thumbs up (π) if it's not just add it as a reply.
-
- 42 replies
Wow it sounds quite epic to me!
Yes nice point (personally I try to keep my messages short for better UX).
replied to
their
post
3 months ago
Yes coming very soon!
replied to
their
post
3 months ago
Yes - we are going to make the list public in the next days!
replied to
their
post
3 months ago
We use our own custom made chat templates that includes a pre-prompt. You can see it here: https://huggingface.co/spaces/huggingchat/chat-ui/blob/main/.env.template#L9
Awesome, you should add some User starter messages for inspiration!
posted
an
update
3 months ago
Post
π₯ New on HuggingChat: Assistants!
Today we are releasing Assistants on HuggingChat!
Assistants are a fun way to package your prompts and share them with the world - powered by Open source Models of course!
Learn more about Assistants here: huggingchat/chat-ui#357
Browse Assistants here: https://huggingface.co/chat/assistants
Today we are releasing Assistants on HuggingChat!
Assistants are a fun way to package your prompts and share them with the world - powered by Open source Models of course!
Learn more about Assistants here: huggingchat/chat-ui#357
Browse Assistants here: https://huggingface.co/chat/assistants
- 11 replies
Interesting π
replied to
their
post
3 months ago
On the Rabbit, all the heavy compute is done remotely I think π
That's really cool! Did you try any alternative to Chroma btw?
Nice read! and I'm really impressed by the quality of the students' projects π€―.
This is the same as OpenAI chat format or is there any difference?
replied to
their
post
4 months ago
Cannot access the demo π
replied to
their
post
4 months ago
Yes, I suppose they do it like this, I could add labels "local"/"remote" on the schema.
replied to
their
post
4 months ago
Not wrong, but you could probably build some nice web browsing agents on top of Mixtral π
posted
an
update
4 months ago
Post
Let's play a little game, how would you build the Rabbit R1 with open source tech? Here is my stack:
- openai/whisper-small for awesome Speech-to-Text with low latency
- mistralai/Mixtral-8x7B-Instruct-v0.1 for an awesome super powerful LLM Brain
- coqui/XTTS-v2 for a nice and clean voice
Which stack will you personally choose?
- openai/whisper-small for awesome Speech-to-Text with low latency
- mistralai/Mixtral-8x7B-Instruct-v0.1 for an awesome super powerful LLM Brain
- coqui/XTTS-v2 for a nice and clean voice
Which stack will you personally choose?
-
- 19 replies
Hi! the feature is not public yet - we'll roll out more invites soon (I added you to the list)
replied to
mariagrandury's
post
4 months ago
Great first post @mariagrandury ! ping @sasha btw :)