Running
512
๐
Kacper Gลombiewski
Clausss
AI & ML interests
None yet
Recent Activity
liked
a Space
1 day ago
Qwen/QVQ-72B-preview
liked
a Space
10 days ago
Xenova/the-tokenizer-playground
Organizations
None yet
Clausss's activity
liked
a
Space
1 day ago
liked
a
Space
10 days ago
reacted to
Spintron's
post with ๐ฅ
20 days ago
Post
1464
Fundamental question. What is the process for sharing an image I have created? Thanks.
- 1 reply
reacted to
nyuuzyou's
post with ๐ฅ
22 days ago
Post
2520
CS2 Highlights Video Dataset -
nyuuzyou/cs2-highlights
A collection of 4,857 high-quality Counter-Strike 2 gameplay highlights featuring:
- Professional and competitive gameplay recordings at 1080p resolution
- Complete metadata including Steam IDs and clip titles
- Preview thumbnails for all videos
- Both 60 FPS (842 clips) and 120 FPS (4,015 clips) content
- Gameplay from Faceit and official competitive modes
This extensive highlights collection provides a valuable resource for developing and evaluating video-based AI applications, especially in esports and competitive gaming contexts. Released under Creative Commons Zero (CC0) license.
A collection of 4,857 high-quality Counter-Strike 2 gameplay highlights featuring:
- Professional and competitive gameplay recordings at 1080p resolution
- Complete metadata including Steam IDs and clip titles
- Preview thumbnails for all videos
- Both 60 FPS (842 clips) and 120 FPS (4,015 clips) content
- Gameplay from Faceit and official competitive modes
This extensive highlights collection provides a valuable resource for developing and evaluating video-based AI applications, especially in esports and competitive gaming contexts. Released under Creative Commons Zero (CC0) license.
liked
a
Space
27 days ago
reacted to
csabakecskemeti's
post with ๐
about 1 month ago
Post
4509
The AMD Instinct MI50 (~$110) is surprisingly fast for inference Quantized models.
This runs a Llama 3.1 8B Q8 with Llama.cpp
https://huggingface.co/spaces/DevQuasar/Mi50
A little blogpost about the HW
http://devquasar.com/uncategorized/amd-radeon-instinct-mi50-cheap-inference/
This runs a Llama 3.1 8B Q8 with Llama.cpp
https://huggingface.co/spaces/DevQuasar/Mi50
A little blogpost about the HW
http://devquasar.com/uncategorized/amd-radeon-instinct-mi50-cheap-inference/
upvoted
an
article
about 1 month ago
Article
Introducing GGUF-my-LoRA
By
โข
โข
13
replied to
nroggendorff's
post
about 2 months ago
so what happen if storage beyond limit?
reacted to
mikelabs's
post with ๐ฅ
about 2 months ago
Post
1597
SAM: I can segment anything!
SAMURAI: Hold my sake while I track it through time and space without even training ๐ฏ
Researchers really said what if we gave SAM object permanence and it worked ๐คฏ
https://www.aimodels.fyi/papers/arxiv/samurai-adapting-segment-anything-model-zero-shot
SAMURAI: Hold my sake while I track it through time and space without even training ๐ฏ
Researchers really said what if we gave SAM object permanence and it worked ๐คฏ
https://www.aimodels.fyi/papers/arxiv/samurai-adapting-segment-anything-model-zero-shot
- 2 replies
Upload 81 files
1
#8 opened about 2 months ago
by
Jorge-Ali
reacted to
fdaudens's
post with โค๏ธ
about 2 months ago
Post
1891
๐ฆ Hug the butterfly! You can now add your Bluesky handle to your Hugging Face profile! โจ
Update app.py
1
#7 opened about 2 months ago
by
yesirecarolinasoto
reacted to
etemiz's
post with ๐ฅ
about 2 months ago
Post
970
if I host in hf spaces, can I interact with the app using an API?
- 1 reply
Error quantizing: b'/bin/sh: 1: ./llama.cpp/llama-quantize: not found\n'
6
#136 opened 2 months ago
by
win10
reacted to
m-ric's
post with ๐
2 months ago
Post
2375
A non-Instruct LLM assistant is mostly useless. ๐ง
Since it's mostly a model trained to complete text, when you ask it a question like "What to do during a stopover in Paris?", it can just go on and on adding more details to your question instead of answering, which would be valid to complete text from its training corpus, but not to answer questions.
โก๏ธ So the post-training stage includes an important Instruction tuning step where you teach your model how to be useful : answer questions, be concise, be polite... RLHF is a well known technique for this.
For people interested to understand how this step works, the folks at Adaptive ML have made a great guide!
Read it here ๐ https://www.adaptive-ml.com/post/from-zero-to-ppo
Since it's mostly a model trained to complete text, when you ask it a question like "What to do during a stopover in Paris?", it can just go on and on adding more details to your question instead of answering, which would be valid to complete text from its training corpus, but not to answer questions.
โก๏ธ So the post-training stage includes an important Instruction tuning step where you teach your model how to be useful : answer questions, be concise, be polite... RLHF is a well known technique for this.
For people interested to understand how this step works, the folks at Adaptive ML have made a great guide!
Read it here ๐ https://www.adaptive-ml.com/post/from-zero-to-ppo