HiDream-ai/HiDream-I1-Full
Text-to-Image
•
Updated
•
16k
•
•
469
Fidite Nemini PRO
FiditeNemini
AI & ML interests
Prompt engineering, unalignment, MLX, model merging, diffusion models
Recent Activity
liked
a model
8 days ago
HiDream-ai/HiDream-I1-Full
Organizations
FiditeNemini's activity
liked
a
model
8 days ago
reacted to
merterbak's
post with 🔥
10 days ago
Post
2943
Meta has unveiled its Llama 4 🦙 family of models, featuring native multimodality and mixture-of-experts architecture. Two model families are available now:
Models🤗: meta-llama/llama-4-67f0c30d9fe03840bc9d0164
Blog Post: https://ai.meta.com/blog/llama-4-multimodal-intelligence/
HF's Blog Post: https://huggingface.co/blog/llama4-release
- 🧠 Native Multimodality - Process text and images in a unified architecture
- 🔍 Mixture-of-Experts - First Llama models using MoE for incredible efficiency
- 📏 Super Long Context - Up to 10M tokens
- 🌐 Multilingual Power - Trained on 200 languages with 10x more multilingual tokens than Llama 3 (including over 100 languages with over 1 billion tokens each)
🔹 Llama 4 Scout
- 17B active parameters (109B total)
- 16 experts architecture
- 10M context window
- Fits on a single H100 GPU
- Beats Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1
🔹 Llama 4 Maverick
- 17B active parameters (400B total)
- 128 experts architecture
- It can fit perfectly on DGX H100(8x H100)
- 1M context window
- Outperforms GPT-4o and Gemini 2.0 Flash
- ELO score of 1417 on LMArena currently second best model on arena
🔹 Llama 4 Behemoth (Coming Soon)
- 288B active parameters (2T total)
- 16 experts architecture
- Teacher model for Scout and Maverick
- Outperforms GPT-4.5, Claude Sonnet 3.7, and Gemini 2.0 Pro on STEM benchmarks
Models🤗: meta-llama/llama-4-67f0c30d9fe03840bc9d0164
Blog Post: https://ai.meta.com/blog/llama-4-multimodal-intelligence/
HF's Blog Post: https://huggingface.co/blog/llama4-release
- 🧠 Native Multimodality - Process text and images in a unified architecture
- 🔍 Mixture-of-Experts - First Llama models using MoE for incredible efficiency
- 📏 Super Long Context - Up to 10M tokens
- 🌐 Multilingual Power - Trained on 200 languages with 10x more multilingual tokens than Llama 3 (including over 100 languages with over 1 billion tokens each)
🔹 Llama 4 Scout
- 17B active parameters (109B total)
- 16 experts architecture
- 10M context window
- Fits on a single H100 GPU
- Beats Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1
🔹 Llama 4 Maverick
- 17B active parameters (400B total)
- 128 experts architecture
- It can fit perfectly on DGX H100(8x H100)
- 1M context window
- Outperforms GPT-4o and Gemini 2.0 Flash
- ELO score of 1417 on LMArena currently second best model on arena
🔹 Llama 4 Behemoth (Coming Soon)
- 288B active parameters (2T total)
- 16 experts architecture
- Teacher model for Scout and Maverick
- Outperforms GPT-4.5, Claude Sonnet 3.7, and Gemini 2.0 Pro on STEM benchmarks
reacted to
clem's
post with 🔥
11 days ago
Post
1923
Llama models (arguably the most successful open AI models of all times) just represented 3% of total model downloads on Hugging Face in March.
People and media like stories of winner takes all & one model/company to rule them all but the reality is much more nuanced than this!
Kudos to all the small AI builders out there!
People and media like stories of winner takes all & one model/company to rule them all but the reality is much more nuanced than this!
Kudos to all the small AI builders out there!
- 2 replies
liked
a
model
23 days ago
liked
a
dataset
26 days ago
reacted to
mlabonne's
post with 🔥
27 days ago
Post
8514
✂️ AutoAbliteration
I made a Colab notebook to automatically abliterate models.
It's quite general, so you can do interesting stuff like blocking a given language in the model outputs.
💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing
I made a Colab notebook to automatically abliterate models.
It's quite general, so you can do interesting stuff like blocking a given language in the model outputs.
💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing
reacted to
AdinaY's
post with 👀
28 days ago
Post
2098
Skywork-R1V🚀 38B open multimodal reasoning model with advanced visual CoT capabilities, released by Skywork.
Skywork/Skywork-R1V-38B
✨ Visual Reasoning: Breaks down complex images step by step.
✨ Math & Science: Solves visual problems with high precision.
✨ Combines text & images for deeper understanding.
Skywork/Skywork-R1V-38B
✨ Visual Reasoning: Breaks down complex images step by step.
✨ Math & Science: Solves visual problems with high precision.
✨ Combines text & images for deeper understanding.
liked
2
models
about 1 month ago
Wrong gguf's in repo?
3
#1 opened about 2 months ago
by
FiditeNemini
reacted to
luigi12345's
post with 👍
about 2 months ago
Post
1781
✅BEST DEBUG PROMPT
Language: Any. 🌀Project Type: Any
Language: Any. 🌀Project Type: Any
What prompt if sent to you will make you detect and fix all the code crashing issues in the COMPLETE codebase so I don't have to ask you to fix again and again ?
Step 1. Gimme such prompt
Step 2 Follow it yourself quietly and COMPLETELY
Step3: State that if you are asked again about finding fatal bugs and logic issues and inconsistencies in the current codebase you would not be able to find more. (You cannot lie, so you must make all the code adjustments necessary prior to such statement).
reacted to
grimjim's
post with 👍
2 months ago
Post
2265
This recent paper points to an explanation for the unreasonable effectiveness of Frankenmerges:
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth
Approach (2502.05171)
Specifically, the duplication of layers in Frankenmerges serves a purpose similar to what occurs in their recurrent-depth architecture. Successful frankenmerges that operate without additional fine-tuning are able to recover or "heal" from any damage due to abrupt transitions between layer blocks. Operational replicated layer blocks can provide functional benefits grounded in latent reasoning. Frankenmerges can also result in hybrid reasoning, by splicing together the latent reasoning of different models.
Back in April 2024, I was able to duplicate a few layers in the Llama 3 8B model, turning it into a 9B model, without harming benchmarks significantly, despite any transition damage.
grimjim/llama-3-experiment-v1-9B
My informal experimentation suggested that latent reasoning circuits could occupy continguous stacks of 2-4 layers, though the result was highly sensitive to the choice of transition location between layers.
Specifically, the duplication of layers in Frankenmerges serves a purpose similar to what occurs in their recurrent-depth architecture. Successful frankenmerges that operate without additional fine-tuning are able to recover or "heal" from any damage due to abrupt transitions between layer blocks. Operational replicated layer blocks can provide functional benefits grounded in latent reasoning. Frankenmerges can also result in hybrid reasoning, by splicing together the latent reasoning of different models.
Back in April 2024, I was able to duplicate a few layers in the Llama 3 8B model, turning it into a 9B model, without harming benchmarks significantly, despite any transition damage.
grimjim/llama-3-experiment-v1-9B
My informal experimentation suggested that latent reasoning circuits could occupy continguous stacks of 2-4 layers, though the result was highly sensitive to the choice of transition location between layers.
- 1 reply
liked
a
dataset
2 months ago
updated
a
model
3 months ago
published
a
model
3 months ago
updated
a
model
3 months ago
published
a
model
3 months ago
reacted to
mkurman's
post with 🔥
3 months ago
Post
1919
I’ve simplified things for the AI OS community!
Check out Qwen-2.5-14B-DeepSeek-R1-1M! This one's a cool blend of the latest Qwen 2.5 with 14 billion parameters and has a massive 1 million token context window. It also comes with the DeepSeek R1 version of the Qwen 2.5 14B base model.
Enjoy! 🚀
mkurman/Qwen2.5-14B-DeepSeek-R1-1M
Check out Qwen-2.5-14B-DeepSeek-R1-1M! This one's a cool blend of the latest Qwen 2.5 with 14 billion parameters and has a massive 1 million token context window. It also comes with the DeepSeek R1 version of the Qwen 2.5 14B base model.
Enjoy! 🚀
mkurman/Qwen2.5-14B-DeepSeek-R1-1M
1M token context version is out
2
#2 opened 3 months ago
by
FiditeNemini
liked
a
model
3 months ago