I didnt mean you lul
I meant him
@MonsterMMORPG
...
alkinun
AtAndDev
AI & ML interests
LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..
Recent Activity
replied to
MonsterMMORPG's
post
1 day ago
Extending Wan 2.1 generated video - First 14b 720p text to video, then using last frame automatically to to generate a video with 14b 720p image to video - with RIFE 32 FPS 10 second 1280x720p video
Our app has this fully automated : https://www.patreon.com/posts/123105403
Here how it works image : https://ibb.co/b582z3R6
Workflow is easy
Use your favorite app to generate initial video.
Get last frame
Give last frame to image to video model - with matching model and resolution
Generate
And merge
Then use MMAudio to add sound
I made it automated in my Wan 2.1 app but can be made with ComfyUI easily as well . I can extend as many as times i want :)
Here initial video
Prompt: Close-up shot of a Roman gladiator, wearing a leather loincloth and armored gloves, standing confidently with a determined expression, holding a sword and shield. The lighting highlights his muscular build and the textures of his worn armor.
Negative Prompt: Overexposure, static, blurred details, subtitles, paintings, pictures, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, redundant fingers, poorly painted hands, poorly painted faces, deformed, disfigured, deformed limbs, fused fingers, cluttered background, three legs, a lot of people in the background, upside down
Used Model: WAN 2.1 14B Text-to-Video
Number of Inference Steps: 20
CFG Scale: 6
Sigma Shift: 10
Seed: 224866642
Number of Frames: 81
Denoising Strength: N/A
LoRA Model: None
TeaCache Enabled: True
TeaCache L1 Threshold: 0.15
TeaCache Model ID: Wan2.1-T2V-14B
Precision: BF16
Auto Crop: Enabled
Final Resolution: 1280x720
Generation Duration: 770.66 seconds
replied to
MonsterMMORPG's
post
2 days ago
Extending Wan 2.1 generated video - First 14b 720p text to video, then using last frame automatically to to generate a video with 14b 720p image to video - with RIFE 32 FPS 10 second 1280x720p video
Our app has this fully automated : https://www.patreon.com/posts/123105403
Here how it works image : https://ibb.co/b582z3R6
Workflow is easy
Use your favorite app to generate initial video.
Get last frame
Give last frame to image to video model - with matching model and resolution
Generate
And merge
Then use MMAudio to add sound
I made it automated in my Wan 2.1 app but can be made with ComfyUI easily as well . I can extend as many as times i want :)
Here initial video
Prompt: Close-up shot of a Roman gladiator, wearing a leather loincloth and armored gloves, standing confidently with a determined expression, holding a sword and shield. The lighting highlights his muscular build and the textures of his worn armor.
Negative Prompt: Overexposure, static, blurred details, subtitles, paintings, pictures, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, redundant fingers, poorly painted hands, poorly painted faces, deformed, disfigured, deformed limbs, fused fingers, cluttered background, three legs, a lot of people in the background, upside down
Used Model: WAN 2.1 14B Text-to-Video
Number of Inference Steps: 20
CFG Scale: 6
Sigma Shift: 10
Seed: 224866642
Number of Frames: 81
Denoising Strength: N/A
LoRA Model: None
TeaCache Enabled: True
TeaCache L1 Threshold: 0.15
TeaCache Model ID: Wan2.1-T2V-14B
Precision: BF16
Auto Crop: Enabled
Final Resolution: 1280x720
Generation Duration: 770.66 seconds
replied to
nroggendorff's
post
2 days ago
200
Organizations
AtAndDev's activity
replied to
MonsterMMORPG's
post
1 day ago
replied to
MonsterMMORPG's
post
2 days ago
brother, dunking on some great models to defend your "product" is not a great (hate to say it but) human value...
replied to
nroggendorff's
post
2 days ago
ma guys suffered ik :)
reacted to
onekq's
post with 😔
3 days ago
Post
1483
I like to benchmark 💵o1-pro💵 but it is way too expensive for me 🤦♂️
-
- 4 replies
Its expensive for everyone, just go with o3-mini, they just figured out that they are not the single llm provider and just doubled the cost of r1 for o3-mini.
reacted to
etemiz's
post with 🚀😎👀
3 days ago
Post
1621
Started fine tuning Gemma 3 using evolutionary approach. It is not the worst model according to AHA leaderboard and it is one of the smart according to lmarena.ai. My objective is to make it based, anti woke, wise, beneficial and then some.
Several GPUs are fine tuning it at the same time, each using a different dataset and using QLoRA and the successful ones are merged later. Compared to LoRa this allows faster training and also reduced overfitting because the merge operation heals overfitting. The problem with this could be the 4 bit quantization may make models dumber. But I am not looking for sheer IQ. Too much mind is a problem anyway :)
Has anyone tried parallel QLoRa and merge before?
I also automated the dataset selection and benchmarking and converging to objectives (the fit function, the reward). It is basically trying to get higher score in AHA Leaderboard as fast as possible with a diverse set of organisms that "evolve by training".
I want to release some cool stuff when I have the time:
- how an answer to a single question changes over time, with each training round or day
- a chart to show AHA alignment over training rounds
Several GPUs are fine tuning it at the same time, each using a different dataset and using QLoRA and the successful ones are merged later. Compared to LoRa this allows faster training and also reduced overfitting because the merge operation heals overfitting. The problem with this could be the 4 bit quantization may make models dumber. But I am not looking for sheer IQ. Too much mind is a problem anyway :)
Has anyone tried parallel QLoRa and merge before?
I also automated the dataset selection and benchmarking and converging to objectives (the fit function, the reward). It is basically trying to get higher score in AHA Leaderboard as fast as possible with a diverse set of organisms that "evolve by training".
I want to release some cool stuff when I have the time:
- how an answer to a single question changes over time, with each training round or day
- a chart to show AHA alignment over training rounds
- 3 replies
posted
an
update
3 days ago
Post
502
Sup yall
Just finished finetuned gemma 3 12b and 27b with a custom rl-like orm for a half-subjective task (rating food and cosmetic products health based on some personal info), tho I want to serve it with a pay-per-token inference engine, does anyone know a platform to host? Btw, as of my knowledge together and some others support lora with a limited list of base models (which do not have gemma 3) so...
More info about that app coming soon :)
We are prepearing to launch...
Stay tooned.
This is getting too long.
See ya
Just finished finetuned gemma 3 12b and 27b with a custom rl-like orm for a half-subjective task (rating food and cosmetic products health based on some personal info), tho I want to serve it with a pay-per-token inference engine, does anyone know a platform to host? Btw, as of my knowledge together and some others support lora with a limited list of base models (which do not have gemma 3) so...
More info about that app coming soon :)
We are prepearing to launch...
Stay tooned.
This is getting too long.
See ya
reacted to
clem's
post with 👀
3 days ago
Post
3173
Should we assemble affordable open-source robots at Hugging Face for the community. Would you buy them? At what price?
- 7 replies
reacted to
clem's
post with 🔥
3 days ago
Post
2284
Nice new space to see how fast your personal or organization followers are growing on HF:
julien-c/follow-history
As you can see, I still have more followers than @julien-c even if he's trying to change this by building such cool spaces 😝😝😝
julien-c/follow-history
As you can see, I still have more followers than @julien-c even if he's trying to change this by building such cool spaces 😝😝😝
replied to
their
post
4 days ago
Also, the links are just wrong as of my knowledge, open source just means its accessible to everyone to download... But the license differs like said, but the worst it can be is not to be used to make money, thats just it.
Please correct me if im wrong.
replied to
their
post
4 days ago
Well, the models are research and there is some real work going into them but I checked some of those products that are promoted here and they are either clones of spaces you can find here and some name added...
Plus, all models here are oss but licensed different like (cc-by-nc or custom licenses) but either way they provide competition, contribution and ideas here which is always plus to everyone.
reacted to
jasoncorkill's
post with 🔥🧠👍
5 days ago
Post
3739
At Rapidata, we compared DeepL with LLMs like DeepSeek-R1, Llama, and Mixtral for translation quality using feedback from over 51,000 native speakers. Despite the costs, the performance makes it a valuable investment, especially in critical applications where translation quality is paramount. Now we can say that Europe is more than imposing regulations.
Our dataset, based on these comparisons, is now available on Hugging Face. This might be useful for anyone working on AI translation or language model evaluation.
Rapidata/Translation-deepseek-llama-mixtral-v-deepl
Our dataset, based on these comparisons, is now available on Hugging Face. This might be useful for anyone working on AI translation or language model evaluation.
Rapidata/Translation-deepseek-llama-mixtral-v-deepl
- 1 reply
replied to
nroggendorff's
post
5 days ago
301
you can use lm-evaluation-harness from Eleuther AI, tho its a bit slow from my testing.
Alternatively, you can use hf evals to match the scores from the public leaderboard.
Side note: The hf llm leaderboard seems to be outdated a bit, so to use the new and better benchmarks, I suggest evaluating locally.
The links:
https://github.com/EleutherAI/lm-evaluation-harness
https://huggingface.co/docs/evaluate/
replied to
their
post
5 days ago
'However, it's important to remember that users have the right to leverage these models commercially without an obligation to contribute.'
Yeah ik, I'm just saying dont promote in here.
Also I didnt mean you specifically, there are promotions or even spams that promote multiple paid gradio app. I'm mad at them not the models...
Thanky you for your kind response btw :)
reacted to
aifeifei798's
post with 👍
6 days ago
Post
3472
😊 This program is designed to remove emojis from a given text. It uses a regular expression (regex) pattern to match and replace emojis with an empty string, effectively removing them from the text. The pattern includes a range of Unicode characters that correspond to various types of emojis, such as emoticons, symbols, and flags. By using this program, you can clean up text data by removing any emojis that may be present, which can be useful for text processing, analysis, or other applications where emojis are not desired. 💻
import re
def remove_emojis(text):
# Define a broader emoji pattern
emoji_pattern = re.compile(
"["
u"\U0001F600-\U0001F64F" # emoticons
u"\U0001F300-\U0001F5FF" # symbols & pictographs
u"\U0001F680-\U0001F6FF" # transport & map symbols
u"\U0001F1E0-\U0001F1FF" # flags (iOS)
u"\U00002702-\U000027B0"
u"\U000024C2-\U0001F251"
u"\U0001F900-\U0001F9FF" # supplemental symbols and pictographs
u"\U0001FA00-\U0001FA6F" # chess symbols and more emojis
u"\U0001FA70-\U0001FAFF" # more symbols and pictographs
u"\U00002600-\U000026FF" # miscellaneous symbols
u"\U00002B50-\U00002B59" # additional symbols
u"\U0000200D" # zero width joiner
u"\U0000200C" # zero width non-joiner
u"\U0000FE0F" # emoji variation selector
"]+", flags=re.UNICODE
)
return emoji_pattern.sub(r'', text)