Post
2044
what should i do for 200 followers... hmmmm... top reply to this post (most emojis) wins, just not anything too crazy
- 11 replies
DedeProGames PRO
DedeProGames
AI & ML interests
Thinking and Agentic Finetuning
Recent Activity
new activity about 5 hours ago
huggingface/InferenceSupport:DedeProGames/DynamicMind-Mini updated a collection about 5 hours ago
DynamicMind new activity about 9 hours ago
StentorLabs/SLM_Arena:Request for new modelOrganizations
reacted to ProCreations's post with 🤝😔🚀😎🔥🤗➕🤯❤️👀🧠👍 3 days ago
reacted to Banaxi-Tech's post with 👀🔥 7 days ago
Post
3599
We're excited to announce BananaMind 2V, our small vision model series!
These models are NOT released yet.
We will release them in mid-august!
BananaMind 2V will include:
BananaMind 2V 256M, the flagship based on BananaMind 2 Pro (BananaMind 2 Pro is not released yet).
BananaMind 2V 100M, our mid model, based on BananaMind 2 Medium.
BananaMind 2V 50M, our smallest vision model, based on BananaMind 2 Mini.
These are currently unreleased and will release in mid-august.
Our training will start after BananaMind 2 Pro has finished training.
These models are NOT released yet.
We will release them in mid-august!
BananaMind 2V will include:
BananaMind 2V 256M, the flagship based on BananaMind 2 Pro (BananaMind 2 Pro is not released yet).
BananaMind 2V 100M, our mid model, based on BananaMind 2 Medium.
BananaMind 2V 50M, our smallest vision model, based on BananaMind 2 Mini.
These are currently unreleased and will release in mid-august.
Our training will start after BananaMind 2 Pro has finished training.
reacted to vineeth98's post with 👍 8 days ago
Post
877
I made a speedrun leaderboard for LoRA fine-tuning. One frozen task (Qwen2.5-1.5B to 57% on GSM8K), one GPU, fastest training run wins. Every record gets re-run 3x with fresh seeds on identical hardware before it counts, so no self-reported numbers.
The baseline was 11:57 three days ago. Someone already got it down to 1:44, with data pruning and a chunked cross-entropy that never materializes the logits.
Attempting is free (Modal's monthly credits cover full runs), and the second track (SmolLM2 + SQuAD) is still sitting at its naive baseline — easy first record for someone.
vineeth98/lora-speedrun
The baseline was 11:57 three days ago. Someone already got it down to 1:44, with data pruning and a chunked cross-entropy that never materializes the logits.
Attempting is free (Modal's monthly credits cover full runs), and the second track (SmolLM2 + SQuAD) is still sitting at its naive baseline — easy first record for someone.
vineeth98/lora-speedrun
- 7 replies
reacted to Leon5201314's post with 🔥 8 days ago
Post
1291
0.7B MonkeyOCRv2 Outperforms Larger Models on 17-Language Document Parsing
MonkeyOCRv2-B-Parsing reaches 83.3 on MDPBench, a multilingual benchmark covering digital-born and photographed documents across 17 languages.
Results among evaluated open-source models:
• MonkeyOCRv2-B, 0.7B: 83.3
• dots.mocr, 3B: 80.5
• HunyuanOCR-1.5, 1B: 76.8
• PaddleOCR-VL-1.6, 0.9B: 75.0
• MinerU2.5-Pro, 1.2B: 71.0
The central idea is simple: before asking an LLM to reason over a document, the vision encoder must preserve every character stroke, digit, punctuation mark, and layout cue.
MonkeyOCRv2 is pretrained on 113M document images across 17 languages using joint image-to-text generation and pixel-level reconstruction.
Models:
https://huggingface.co/collections/zenosai/monkeyocrv2
Paper:
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI (2607.11562)
GitHub:
https://github.com/Yuliang-Liu/MonkeyOCRv2
Code and model weights are available under Apache-2.0.
We welcome tests on difficult multilingual, photographed, and visually ambiguous documents—especially failure cases.
MonkeyOCRv2-B-Parsing reaches 83.3 on MDPBench, a multilingual benchmark covering digital-born and photographed documents across 17 languages.
Results among evaluated open-source models:
• MonkeyOCRv2-B, 0.7B: 83.3
• dots.mocr, 3B: 80.5
• HunyuanOCR-1.5, 1B: 76.8
• PaddleOCR-VL-1.6, 0.9B: 75.0
• MinerU2.5-Pro, 1.2B: 71.0
The central idea is simple: before asking an LLM to reason over a document, the vision encoder must preserve every character stroke, digit, punctuation mark, and layout cue.
MonkeyOCRv2 is pretrained on 113M document images across 17 languages using joint image-to-text generation and pixel-level reconstruction.
Models:
https://huggingface.co/collections/zenosai/monkeyocrv2
Paper:
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI (2607.11562)
GitHub:
https://github.com/Yuliang-Liu/MonkeyOCRv2
Code and model weights are available under Apache-2.0.
We welcome tests on difficult multilingual, photographed, and visually ambiguous documents—especially failure cases.
- 1 reply
reacted to salma-remyx's post with 👀 8 days ago
Post
2897
Your coding agent is waiting on you to decide what to try next.
It doesn't originate that decision on its own.
What's usually missing is a way to generate that decision systematically, grounded in something more than the random paper that came across someone's feed that week.
Outrider starts from research with code and data behind it to scope a change applying the core method in your own codebase. A feature branch gets gated on your own evaluation methods before it reaches you in review.
The result is tied to what actually happened in your system, not to a model's read on its own output.
Here's what a code recommendation system looks like end to end.
It doesn't originate that decision on its own.
What's usually missing is a way to generate that decision systematically, grounded in something more than the random paper that came across someone's feed that week.
Outrider starts from research with code and data behind it to scope a change applying the core method in your own codebase. A feature branch gets gated on your own evaluation methods before it reaches you in review.
The result is tied to what actually happened in your system, not to a model's read on its own output.
Here's what a code recommendation system looks like end to end.
- 7 replies
reacted to appvoid's post with 👀 11 days ago
Post
257
small reasoning models are overrated, these little ones just doom loop a lot by default. good data will always be the moat when training or finetuning small models and latest sota models like fable 5 and gpt 5.6 are increasingly making this a lot easier to do.
- 3 replies
reacted to their post with 👍 13 days ago
Post
375
🚀 Introducing the GRM-2.6 Family
The GRM-2.6 family is a new generation of reasoning-focused models from Orion LLM Labs, built for difficult tasks, coding, STEM, terminal agents, and advanced local AI workflows.
GRM-2.6-Plus is the main high-capability model in the family: a 27B-class reasoning model based on Qwen3.6, designed for strong structured reasoning, coding, agentic use, and practical local deployment.
GRM-2.6-Opus builds on GRM-2.6-Plus as a merge with an Opus-style reasoning distilled model, improving structured reasoning behavior, terminal-agent workflows, coding ability, and complex problem solving.
Both models are designed for users who want powerful reasoning models that remain practical for research, local inference, coding, and agent experiments.
Models:
GRM-2.6-Plus: OrionLLM/GRM-2.6-Plus
GRM-2.6-Opus: OrionLLM/GRM-2.6-Opus
Organization:
OrionLLM
The GRM-2.6 family is a new generation of reasoning-focused models from Orion LLM Labs, built for difficult tasks, coding, STEM, terminal agents, and advanced local AI workflows.
GRM-2.6-Plus is the main high-capability model in the family: a 27B-class reasoning model based on Qwen3.6, designed for strong structured reasoning, coding, agentic use, and practical local deployment.
GRM-2.6-Opus builds on GRM-2.6-Plus as a merge with an Opus-style reasoning distilled model, improving structured reasoning behavior, terminal-agent workflows, coding ability, and complex problem solving.
Both models are designed for users who want powerful reasoning models that remain practical for research, local inference, coding, and agent experiments.
Models:
GRM-2.6-Plus: OrionLLM/GRM-2.6-Plus
GRM-2.6-Opus: OrionLLM/GRM-2.6-Opus
Organization: