Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
90.0
TFLOPS
112
16
251
s3nh
s3nh
Follow
hayden-donnelly's profile picture
Bujurocks's profile picture
svjack's profile picture
247 followers
·
93 following
s3nhs3nh
s3nh
AI & ML interests
Quantization, LLMs, Deep Learning for good. Follow me if you like my work. Patreon.com/s3nh
Recent Activity
reacted
to
Severian
's
post
with 👍
about 18 hours ago
MLX port of BDH (Baby Dragon Hatchling) is up! I’ve ported the BDH ( https://github.com/pathwaycom/bdh ) model to MLX for Apple Silicon. It’s a faithful conversion of the PyTorch version: same math, same architecture (byte-level vocab, shared weights across layers, ReLU sparsity, RoPE attention with Q=K), with MLX-friendly APIs and a detailed README explaining the few API-level differences and why results are equivalent. Code, docs, and training script are ready to use. You may need to adjust the training script a bit to fit your own custom dataset. Only tested on M4 so far, but should work perfect for any M1/M2/M3 users out there. I’m currently training this MLX build on my Internal Knowledge Map (IKM) dataset https://huggingface.co/datasets/Severian/Internal-Knowledge-Map Training’s underway; expect a day or so before I publish weights. When it’s done, I’ll upload the checkpoint to Hugging Face for anyone to test. Repo: https://github.com/severian42/BDH-MLX HF model (coming soon): https://huggingface.co/Severian/BDH-MLX If you try it on your own data, feedback and PRs are welcome.
reacted
to
mitkox
's
post
with 🚀
about 19 hours ago
Hermes4 70B synthetic dataset generation on my desktop Z8 GPU rig: 307 tok/sec 1.1M tok/hour The bottleneck for generating massive, high-quality reinforcement learning datasets is never the GPU compute; it's always the model's willingness to actually answer the darn question.
liked
a model
about 21 hours ago
Jackmin108/glm-0.5B
View all activity
Organizations
s3nh
's models
438
Sort: Recently updated
s3nh/Guilherme34-Samantha-v2-GGUF
Text Generation
•
7B
•
Updated
Jan 6, 2024
•
7
•
1
s3nh/Hermes-SolarMaid-7b
Text Generation
•
7B
•
Updated
Jan 6, 2024
•
1
•
1
s3nh/Masterjp123-NeuralMaid-7b-GGUF
Text Generation
•
7B
•
Updated
Jan 6, 2024
•
7
•
1
s3nh/Azazelle-Tippy-Toppy-7b-GGUF
Text Generation
•
7B
•
Updated
Jan 6, 2024
•
20
s3nh/Azazelle-Maylin-7b-GGUF
Text Generation
•
7B
•
Updated
Jan 6, 2024
•
7
s3nh/Azazelle-Yuna-7b-Merge-GGUF
Text Generation
•
7B
•
Updated
Jan 6, 2024
•
7
s3nh/phanerozoic-Mistral-Pirate-7b-v0.3-GGUF
Text Generation
•
7B
•
Updated
Jan 4, 2024
•
12
s3nh/NeuralNovel-Tanuki-7B-v0.1-GGUF
Text Generation
•
7B
•
Updated
Jan 4, 2024
•
8
•
1
s3nh/phanerozoic-Tiny-Pirate-1.1b-v0.1-GGUF
Text Generation
•
Updated
Jan 4, 2024
s3nh/sethuiyer-SynthIQ-7b-GGUF
Text Generation
•
7B
•
Updated
Jan 4, 2024
•
5
•
1
s3nh/Delcos-Velara-11B-V2-GGUF
Text Generation
•
11B
•
Updated
Jan 4, 2024
•
7
•
1
s3nh/s3nh-phi-2-Evol-Instruct-Chinese-GGUF
Text Generation
•
Updated
Jan 4, 2024
s3nh/bibidentuhanoi-BMO-7B-Instruct-GGUF
Text Generation
•
7B
•
Updated
Jan 4, 2024
•
7
s3nh/Yash21-TinyYi-7b-GGUF
Text Generation
•
9B
•
Updated
Jan 4, 2024
•
7
s3nh/allbyai-ToRoLaMa-7b-v1.0-GGUF
Text Generation
•
Updated
Jan 4, 2024
s3nh/GeneZC-MiniChat-2-3B-GGUF
Text Generation
•
3B
•
Updated
Jan 4, 2024
•
6
•
2
s3nh/laurentiubp-trained-stocks-3B-GGUF
Text Generation
•
Updated
Jan 3, 2024
s3nh/mlabonne-NeuralPipe-7B-slerp-GGUF
Text Generation
•
7B
•
Updated
Jan 3, 2024
•
7
•
1
s3nh/abacusai-Giraffe-13b-32k-v3-GGUF
Text Generation
•
13B
•
Updated
Jan 3, 2024
•
14
•
2
s3nh/OEvortex-HelpingAI-Lite-GGUF
Text Generation
•
Updated
Jan 3, 2024
s3nh/ibleducation-ibl-neural-edu-content-7B-GGUF
Updated
Jan 3, 2024
s3nh/Undi95-Unholy-v2-13B-GGUF
Text Generation
•
13B
•
Updated
Jan 3, 2024
•
9
•
1
s3nh/OEvortex-HelpingAI-GGUF
Text Generation
•
7B
•
Updated
Jan 3, 2024
•
9
s3nh/elonmollusk-neuralogix-neural-chat-v1-GGUF
Text Generation
•
7B
•
Updated
Jan 3, 2024
•
9
•
2
s3nh/Walmart-the-bag-WordWoven-13B-GGUF
Text Generation
•
Updated
Jan 2, 2024
s3nh/AdaptLLM-medicine-LLM-13B-GGUF
Text Generation
•
13B
•
Updated
Jan 2, 2024
•
119
•
1
s3nh/AdaptLLM-finance-LLM-13B-GGUF
Text Generation
•
13B
•
Updated
Jan 2, 2024
•
133
•
6
s3nh/openerotica-cockatrice-7b-v0.2-GGUF
Text Generation
•
7B
•
Updated
Jan 2, 2024
•
36
•
2
s3nh/decapoda-research-Antares-11b-v1-GGUF
Text Generation
•
11B
•
Updated
Jan 1, 2024
•
115
•
1
s3nh/DopeorNope-Mark1-10.7B-GGUF
Text Generation
•
11B
•
Updated
Jan 1, 2024
•
7
Previous
1
...
4
5
6
7
8
...
15
Next