lodestones/Kroma
Text-to-Image • Updated • 95
Ron
ronedgecomb
AI & ML interests
EVERYTHING TECHNOLOGY
Recent Activity
liked a model about 1 hour ago
lodestones/Kroma liked a model about 10 hours ago
meituan-longcat/LongCat-Flash-Lite-Sparse liked a model about 10 hours ago
unsloth/Inkling-SmallOrganizations
None yet
liked a
model about 1 hour ago
liked 2
models about 10 hours ago
reacted to Enderchef's post with ❤️ about 10 hours ago
Post
953
I've left Glint Research.
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.
While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.
AxiomicLabs
fromziro
SupraLabs
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.
While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.
- 2 replies
liked a
model about 10 hours ago
liked 2
models 2 days ago
liked a
model 3 days ago
upvoted a paper 3 days ago
liked 4
models 3 days ago
FunAudioLLM/Fun-ASR-Nano-2512-GGUF
Automatic Speech Recognition • Updated • 149 • 4
bottlecapai/ThinkingCap-Qwen3.6-27B-NVFP4
Image-Text-to-Text • 17B • Updated • 3.06k • 6
Audio8/Audio8-TTS-Preview-0.6b
Text-to-Speech • 0.6B • Updated • 3.25k • 166
poolside/Laguna-S-2.1-DFlash-NVFP4
1B • Updated • 44.9k • 31
liked a
model 4 days ago
reacted to julien-c's post with 🤗 4 days ago
Post
3853
who's working on an NVFP4 version of Kimi-K3?
- 4 replies
liked 4
models 4 days ago
Qwen/WebWorld-32B
Text Generation • 677k • Updated • 402 • 76
NousResearch/Yarn-Llama-2-7b-128k
Text Generation • Updated • 1.02k • 41
nvidia/llama-nemotron-embed-vl-1b-v2-fp8
Sentence Similarity • 2B • Updated • 517 • 12
nvidia/llama-nemotron-rerank-vl-1b-v2-fp8
Text Ranking • 2B • Updated • 84 • 5
reacted to FredyRivera-dev's post with 🚀 4 days ago
Post
6253
We wrote a full technical guide on how to train a bilingual (ES/EN) LLM from scratch: TinyQwen.
Covers:
- Hybrid architecture based on Qwen3.5
- Pre-training with 15B tokens
- Cost benchmark between H200 and B200
- Post-training with SFT + LoRA
- Full code and data, open source
With ~$11 of compute on an H200 we ran an initial training run, enough to validate the full architecture and pipeline.
Blog post: https://aquiles-ai.vercel.app/blog/tinyqwen-from-scratch
Technical feedback welcome, especially from anyone looking to replicate the pipeline with more compute.
Covers:
- Hybrid architecture based on Qwen3.5
- Pre-training with 15B tokens
- Cost benchmark between H200 and B200
- Post-training with SFT + LoRA
- Full code and data, open source
With ~$11 of compute on an H200 we ran an initial training run, enough to validate the full architecture and pipeline.
Blog post: https://aquiles-ai.vercel.app/blog/tinyqwen-from-scratch
Technical feedback welcome, especially from anyone looking to replicate the pipeline with more compute.
- 3 replies