Stable Diffusion Community (Unofficial, Non-profit)

community

AI & ML interests

Enhance and upgrade SD-models

sd-community's activity

ehristoforuΒ 
posted an update 4 days ago
view post
Post
2534
Introducing our first standalone model – 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:
πŸ† 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
  • 4 replies
Β·
AtAndDevΒ 
posted an update 13 days ago
view post
Post
2381
@nroggendorff is that you sama?
  • 2 replies
Β·
eienmojikiΒ 
posted an update 21 days ago
ameerazam08Β 
posted an update 29 days ago
not-lainΒ 
posted an update 30 days ago
AtAndDevΒ 
posted an update about 1 month ago
view post
Post
1882
everywhere i go i see his face
AtAndDevΒ 
posted an update about 1 month ago
view post
Post
528
Deepseek gang on fire fr fr
AtAndDevΒ 
posted an update about 1 month ago
view post
Post
1611
R1 is out! And with a lot of other R1 releated models...
not-lainΒ 
posted an update about 1 month ago
view post
Post
1633
we now have more than 2000 public AI models using ModelHubMixinπŸ€—
not-lainΒ 
posted an update about 2 months ago
view post
Post
4013
Published a new blogpost πŸ“–
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
πŸ”— https://huggingface.co./blog/not-lain/tensor-dims
some interesting takeaways :
1aurentΒ 
posted an update about 2 months ago
ehristoforuΒ 
posted an update 2 months ago
view post
Post
3465
βœ’οΈ Ultraset - all-in-one dataset for SFT training in Alpaca format.
fluently-sets/ultraset

❓ 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.

🀯 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.

πŸ€— 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.

❇️ Ultraset is an excellent tool to improve your language model's skills in diverse knowledge areas.
AtAndDevΒ 
posted an update 2 months ago
view post
Post
462
@s3nh Hey man check your discord! Got some news.
  • 4 replies
Β·
not-lainΒ 
posted an update 4 months ago
view post
Post
2316
ever wondered how you can make an API call to a visual-question-answering model without sending an image url πŸ‘€

you can do that by converting your local image to base64 and sending it to the API.

recently I made some changes to my library "loadimg" that allows you to make converting images to base64 a breeze.
πŸ”— https://github.com/not-lain/loadimg

API request example πŸ› οΈ:
from loadimg import load_img
from huggingface_hub import InferenceClient

# or load a local image
my_b64_img = load_img(imgPath_url_pillow_or_numpy ,output_type="base64" ) 

client = InferenceClient(api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")

messages = [
	{
		"role": "user",
		"content": [
			{
				"type": "text",
				"text": "Describe this image in one sentence."
			},
			{
				"type": "image_url",
				"image_url": {
					"url": my_b64_img # base64 allows using images without uploading them to the web
				}
			}
		]
	}
]

stream = client.chat.completions.create(
    model="meta-llama/Llama-3.2-11B-Vision-Instruct", 
	messages=messages, 
	max_tokens=500,
	stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="")
KingNishΒ 
posted an update 5 months ago
KingNishΒ 
posted an update 5 months ago
view post
Post
8249
Exciting news! Introducing super-fast AI video assistant, currently in beta. With a minimum latency of under 500ms and an average latency of just 600ms.

DEMO LINK:
KingNish/Live-Video-Chat
  • 1 reply
Β·