Robust and Fine-Grained Detection of AI Generated Texts
Paper
β’
2504.11952
β’
Published
β’
4
Stable Diffusion Community (Unofficial, Non-profit)
community
AI & ML interests
Enhance and upgrade SD-models
Recent Activity
sd-community's activity
1024mΒ
authored
a
paper
about 23 hours ago
Post
380
gen z boss and a o3-mini
gen z boss and a o3-mini
gen z boss and a o3-mini
1024mΒ
authored
a
paper
3 days ago
1024mΒ
authored
a
paper
8 days ago
Post
4208
There seems to multiple paid apps shared here that are based on models on hf, but some ppl sell their wrappers as "products" and promote them here. For a long time, hf was the best and only platform to do oss model stuff but with the recent AI website builders anyone can create a product (really crappy ones btw) and try to sell it with no contribution to oss stuff. Please dont do this, or try finetuning the models you use...
Sorry for filling yall feed with this bs but yk...
Sorry for filling yall feed with this bs but yk...
- 6 replies
Post
1600
Gemma 3 seems to be really good at human preference. Just waiting for ppl to see it.
Post
2044
πAraClip is now fully integrated with Hugging Face π€
AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasksπ₯
π Try it out π
π€ model: Arabic-Clip/araclip
𧩠Gradio demo: Arabic-Clip/Araclip-Simplified
π website: https://arabic-clip.github.io/Arabic-CLIP/
AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasksπ₯
π Try it out π
π€ model: Arabic-Clip/araclip
𧩠Gradio demo: Arabic-Clip/Araclip-Simplified
π website: https://arabic-clip.github.io/Arabic-CLIP/
- 2 replies
ehristoforuΒ
posted
an
update
about 2 months ago
Post
3030
Introducing our first standalone model β FluentlyLM Prinum
Introducing the first standalone model from Project Fluently LM! We worked on it for several months, used different approaches and eventually found the optimal one.
General characteristics:
- Model type: Causal language models (QwenForCausalLM, LM Transformer)
- Number of parameters: 32.5B
- Number of parameters (not embedded): 31.0B
- Number of layers: 64
- Context: 131,072 tokens
- Language(s) (NLP): English, French, Spanish, Russian, Chinese, Japanese, Persian (officially supported)
- License: MIT
Creation strategy:
The basis of the strategy is shown in Pic. 2.
We used Axolotl & Unsloth for SFT-finetuning with PEFT LoRA (rank=64, alpha=64) and Mergekit for SLERP and TIES mergers.
Evolution:
π 12th place in the Open LLM Leaderboard ( open-llm-leaderboard/open_llm_leaderboard) (21.02.2025)
Detailed results and comparisons are presented in Pic. 3.
Links:
- Model: fluently-lm/FluentlyLM-Prinum
- GGUF version: mradermacher/FluentlyLM-Prinum-GGUF
- Demo on ZeroGPU: ehristoforu/FluentlyLM-Prinum-demo
Introducing the first standalone model from Project Fluently LM! We worked on it for several months, used different approaches and eventually found the optimal one.
General characteristics:
- Model type: Causal language models (QwenForCausalLM, LM Transformer)
- Number of parameters: 32.5B
- Number of parameters (not embedded): 31.0B
- Number of layers: 64
- Context: 131,072 tokens
- Language(s) (NLP): English, French, Spanish, Russian, Chinese, Japanese, Persian (officially supported)
- License: MIT
Creation strategy:
The basis of the strategy is shown in Pic. 2.
We used Axolotl & Unsloth for SFT-finetuning with PEFT LoRA (rank=64, alpha=64) and Mergekit for SLERP and TIES mergers.
Evolution:
π 12th place in the Open LLM Leaderboard ( open-llm-leaderboard/open_llm_leaderboard) (21.02.2025)
Detailed results and comparisons are presented in Pic. 3.
Links:
- Model: fluently-lm/FluentlyLM-Prinum
- GGUF version: mradermacher/FluentlyLM-Prinum-GGUF
- Demo on ZeroGPU: ehristoforu/FluentlyLM-Prinum-demo
-
-
- 7 replies
ameerazam08Β
posted
an
update
3 months ago
Post
4380
I have just released a new blogpost about kv caching and its role in inference speedup π
π https://huggingface.co/blog/not-lain/kv-caching/
some takeaways :
π https://huggingface.co/blog/not-lain/kv-caching/
some takeaways :
-
- 4 replies
Post
1624
R1 is out! And with a lot of other R1 releated models...
Post
1696
we now have more than 2000 public AI models using ModelHubMixinπ€
Post
4059
Published a new blogpost π
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
π https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
π https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
Post
943
Hey everyone π€!
Check out this new Virtual Try Off model (based on SD1.5): 1aurent/TryOffAnyone
This model isn't as accurate as others (e.g. xiaozaa/cat-try-off-flux based on FLUX.1) but it sure is fast!
Check out this new Virtual Try Off model (based on SD1.5): 1aurent/TryOffAnyone
This model isn't as accurate as others (e.g. xiaozaa/cat-try-off-flux based on FLUX.1) but it sure is fast!
ehristoforuΒ
posted
an
update
4 months ago
Post
3879
βοΈ Ultraset - all-in-one dataset for SFT training in Alpaca format.
fluently-sets/ultraset
β Ultraset is a comprehensive dataset for training Large Language Models (LLMs) using the SFT (instruction-based Fine-Tuning) method. This dataset consists of over 785 thousand entries in eight languages, including English, Russian, French, Italian, Spanish, German, Chinese, and Korean.
π€― Ultraset solves the problem faced by users when selecting an appropriate dataset for LLM training. It combines various types of data required to enhance the model's skills in areas such as text writing and editing, mathematics, coding, biology, medicine, finance, and multilingualism.
π€ For effective use of the dataset, it is recommended to utilize only the "instruction," "input," and "output" columns and train the model for 1-3 epochs. The dataset does not include DPO or Instruct data, making it suitable for training various types of LLM models.
βοΈ Ultraset is an excellent tool to improve your language model's skills in diverse knowledge areas.
fluently-sets/ultraset
β Ultraset is a comprehensive dataset for training Large Language Models (LLMs) using the SFT (instruction-based Fine-Tuning) method. This dataset consists of over 785 thousand entries in eight languages, including English, Russian, French, Italian, Spanish, German, Chinese, and Korean.
π€― Ultraset solves the problem faced by users when selecting an appropriate dataset for LLM training. It combines various types of data required to enhance the model's skills in areas such as text writing and editing, mathematics, coding, biology, medicine, finance, and multilingualism.
π€ For effective use of the dataset, it is recommended to utilize only the "instruction," "input," and "output" columns and train the model for 1-3 epochs. The dataset does not include DPO or Instruct data, making it suitable for training various types of LLM models.
βοΈ Ultraset is an excellent tool to improve your language model's skills in diverse knowledge areas.
