Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

Local LLMs

Recent Activity
OzTianlu  authored a paper 7 days ago
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
OzTianlu  submitted a paper 8 days ago
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
OzTianlu  authored a paper about 1 month ago
A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics
View all activity
prithivMLmods 
posted an update about 2 hours ago
view post
Post
9
Wan2.2-I2V-Fast with highly upscaled sequential frame sampling is now available as a Spaces demo, built using Wan2.2-I2V and FLUX.2-Klein. Try the demo using the links below.👇

➠ wan2.2-i2v-fast : prithivMLmods/wan2.2-i2v-fast
➠ github: https://github.com/prithivsakthiur/wan2.2-i2v-fast
➠ collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

⤷ To learn more, visit the app page or the respective model pages.
OzTianlu 
posted an update 2 days ago
view post
Post
6182
ResNet is Explicit Euler. GPT is Implicit Euler. What Else is Hiding in Plain Sight?

Read online: https://datawhalechina.github.io/learning-terrain/

I wrote an open-source monograph on learning dynamics — The Terrain of Learning. Bilingual (Chinese/English), 4 volumes, 12 chapters, 30+ print-grade figures. Completely free (CC BY-NC-SA 4.0).

The core argument: gradient descent is not optimization. It's terrain motion. The loss function is a landscape. The gradient is the direction of slope. The optimizer is how you choose each step. Once you see it this way, everything clicks:

ResNet = explicit Euler integration on a vector field. The residual branch is the vector field. Each layer takes one Euler step.

GPT autoregression = implicit-state Euler iteration. Stable where explicit Euler explodes. That's why transformers handle long-range dependencies.

DEQ = the Banach fixed-point theorem in production. The forward pass is root-finding. There are no layers to backprop through.

KL divergence = a Bregman divergence on the entropy landscape. Your belief space is curved, not flat.

Chain-of-thought reasoning = hidden states flowing along a reasoning field toward an attractor basin. Correct answers have wide basins. The number of reasoning steps is determined by the terrain, not by the problem.

Diffusion models = systems flowing downhill along a score vector field, from noise to structure, from high energy to low energy.

The book traces one idea across 337 years — from F=ma (Newton, 1687) to H=T+V (Hamilton, 1833) to loss landscape + gradient field (2020s). Hamilton replaced a catalog of forces with one geometric object. This book does the same for deep learning.

GitHub: https://github.com/datawhalechina/learning-terrain
Discussion: https://github.com/datawhalechina/learning-terrain/discussions/2

Convergence is not hope. Convergence is geometry. You see.
  • 1 reply
·
OzTianlu 
authored a paper 7 days ago
OzTianlu 
submitted a paper to Daily Papers 8 days ago
pankajpandey-dev 
posted an update 9 days ago
view post
Post
896
🇮🇳 Gemma-3-1B Hindi Instruct — a Hindi LLM that runs fully offline, anywhere.
Last week I shipped Qwen3-4B Hindi. This week I went the other direction: how tiny can a useful Hindi model get? So I fine-tuned Gemma-3-1B on quality-filtered Hindi instruction data and shipped the full GGUF ladder.
✅ Fine-tune (16-bit): pankajpandey-dev/gemma-3-1b-hindi-instruct
✅ GGUF (Q4/Q5/Q8): pankajpandey-dev/gemma-3-1b-hindi-instruct-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 806 MB — runs on CPU, a cheap laptop, even a Raspberry Pi.
What I tried this round: chrF-filtered the training data to drop weak translations, and used response-only loss so the model learns how to answer, not how to repeat prompts.
Honest note: at 1B, Hindi fluency is strong but coherence is bounded by size — it's a lightweight/edge experiment, not a 4B replacement. Gemma-3-4B Hindi is next.
Part of my Hindi LLM Series — openly-licensed Indic models for local & edge use. Feedback welcome 🙏
#Hindi #IndicNLP #GGUF #LocalLLM #Gemma #EdgeAI
prithivMLmods 
posted an update 15 days ago
pankajpandey-dev 
posted an update 16 days ago
view post
Post
14972
🇮🇳 Qwen3-4B Hindi Instruct v2 — a Hindi LLM that runs on your own machine
Most strong Hindi-capable models are either huge or cloud-only. I wanted one that's small enough to run locally but actually follows instructions in Hindi — so I fine-tuned Qwen3-4B on 10K Hindi instruction pairs and shipped it with a full GGUF quant ladder.
✅ Fine-tune (16-bit): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2
✅ GGUF (Q4/Q5/Q8): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 2.5 GB — fits comfortably on a laptop, CPU or GPU.
Part of my Hindi LLM Series — building openly-licensed Indic models for local and edge use. More coming (Gemma next). Feedback welcome 🙏
#Hindi #IndicNLP #GGUF #LocalLLM #Qwen
  • 4 replies
·
prithivMLmods 
posted an update 18 days ago
view post
Post
6150
PiD — Pixel Diffusion Decoder Image Edit Upscale and Image Generation Upscale, an all-in-one demo, is now live on Spaces! Great improvements in realism-based image generation and editing are powered by FLUX.2-Klein, while image generation is paired with Z-Image, and upscaling is enabled by default!

🤗 Space: prithivMLmods/PiD-Image-Upscaler
🔗 Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

🤗 > To learn more, visit the app page or the respective model pages.
pankajpandey-dev 
posted an update 20 days ago
view post
Post
691
🇮🇳 Just shipped: MiniCPM5-1B-Hindi-Instruct (+ GGUF quants)

First Hindi instruction-tuned fine-tune of OpenBMB's brand-new MiniCPM5-1B (released this week).

Trained with Unsloth + LoRA (r=32) on AI4Bharat's anudesh + dolly Hindi splits — ~4k high-quality examples, 2 epochs on a single T4 in 60 minutes.

🔗 Model (16-bit + LoRA adapter):
pankajpandey-dev/MiniCPM5-1B-Hindi-Instruct

📦 GGUF quants for llama.cpp / Ollama / LM Studio:
pankajpandey-dev/MiniCPM5-1B-Hindi-Instruct-v1-GGUF

5 quant levels — from Q3_K_M (~560 MB, runs on a Raspberry Pi) to Q8_0 (~1.2 GB, near-lossless). Q4_K_M is the recommended default.

Part of my ongoing 🇮🇳 Hindi LLM Series — bringing strong open-source LLMs to Indian languages.

#Hindi #IndicNLP #MiniCPM5 #LoRA #Unsloth #GGUF #llamacpp #Ollama #LocalLLM
pankajpandey-dev 
posted an update 21 days ago
view post
Post
2695
🧬 Just uploaded K-quants of Carbon-3B for llama.cpp users!
@HuggingFaceBio released the original GGUF in bf16 only — so I added the full quant ladder for CPU/edge inference:
• Q2_K → 1.4 GB
• Q3_K_M → 1.8 GB
• Q4_K_M → 2.1 GB ⭐
• Q5_K_M → 2.4 GB
• Q6_K → 2.7 GB
• Q8_0 → 3.5 GB
🔗 pankajpandey-dev/Carbon-3B-GGUF
Now you can generate DNA sequences on your laptop. Needs a llama.cpp build with PR #23410 (HybridDNATokenizer support).
Huge thanks to the HuggingFaceBio team for the original model 🙏
#GGUF #llamacpp #genomics #DNA
pankajpandey-dev 
posted an update 23 days ago
view post
Post
276
Just released Qwen3-0.6B fine-tuned on Hindi instruction data 🇮🇳

✅ Full model: pankajpandey-dev/Qwen3-0.6B-Hindi-Instruct-v1
✅ GGUF versions (Q2/Q4/Q5/Q8): pankajpandey-dev/Qwen3-0.6B-Hindi-Instruct-v1-GGUF

Smallest Hindi-capable GGUF — runs on any laptop at 0.37GB.
Next: v2 with more data, better responses.

#Hindi #LLM #GGUF #OpenSource
prithivMLmods 
posted an update 25 days ago
view post
Post
5575
I've made 8 Spaces in the Qwen-Image-Edit series, and out of them, 5 Spaces reached “Space of the Week”! A few Spaces are still topping the list even after many months.

Cumulatively, the series has crossed 8.2 million+ ZeroGPU runs and nearly 4 million visitors overall.

Thanks for all the community support! 🤗❤️

🔗 Spaces: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
  • 4 replies
·
OzTianlu 
authored a paper about 1 month ago
OzTianlu 
submitted a paper to Daily Papers about 1 month ago
Aurelien-Morgan 
posted an update about 1 month ago
view post
Post
1089
@retrain-pipelines v0.2.0 is out !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
  • 1 reply
·
Ujjwal-Tyagi 
posted an update about 1 month ago
view post
Post
363
6 Open-Source Libraries to FineTune LLMs
1. Unsloth
GitHub: https://github.com/unslothai/unsloth
→ Fastest way to fine-tune LLMs locally
→ Optimized for low VRAM (even laptops)
→ Plug-and-play with Hugging Face models

2. Axolotl
GitHub: https://github.com/OpenAccess-AI-Collective/axolotl
→ Flexible LLM fine-tuning configs
→ Supports LoRA, QLoRA, multi-GPU
→ Great for custom training pipelines

3. TRL (Transformer Reinforcement Learning)
GitHub: https://github.com/huggingface/trl
→ RLHF, DPO, PPO for LLM alignment
→ Built on Hugging Face ecosystem
→ Essential for post-training optimization

4. DeepSpeed
GitHub: https://github.com/microsoft/DeepSpeed
→ Train massive models efficiently
→ Memory + speed optimization
→ Industry standard for scaling

5. LLaMA-Factory
GitHub: https://github.com/hiyouga/LLaMA-Factory
→ All-in-one fine-tuning UI + CLI
→ Supports multiple models (LLaMA, Qwen, etc.)
→ Beginner-friendly + powerful

6. PEFT
GitHub: https://github.com/huggingface/peft
→ Fine-tune with minimal compute
→ LoRA, adapters, prefix tuning
→ Best for cost-efficient training
  • 1 reply
·
Sri-Vigneshwar-DJ 
posted an update about 1 month ago
view post
Post
149
![Feather DB LongMemEval Results]( Hawky-ai/longmemeval-results)

We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) — 500 questions across real multi-session conversations, up to 115K tokens each.

**Score: 0.693** · GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**

Per-axis breakdown:
→ Info-extraction: **0.942**
→ Knowledge-update: **0.714**
→ Multi-session: **0.606**
→ Temporal: **0.477** ← the hard one, Phase 9 addresses this

Architecture: Hybrid BM25+dense · adaptive temporal decay · embedded (no server) · p50 = 0.19ms · MIT

pip install feather-db

Raw results + audit JSONs: Hawky-ai/longmemeval-results
prithivMLmods 
posted an update about 2 months ago
view post
Post
5938
Multimodal-Edge Demo, a node-based inference canvas demo, is now live on Spaces. It features node-based Transformers for fast inference across 10+ edge-device multimodal models on the Hub, all within a single space. The series includes models from Qwen3.5, Qwen3-VL, Gemma 4, and the LFM 2.5 VL model series, with support for reasoning and grounding tasks.

🤗 Demo: prithivMLmods/Multimodal-Edge-Node
🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/Multimodal-Edge-Node
✅ Multimodal Apps Collections: https://huggingface.co/collections/prithivMLmods/hall-of-multimodal-apps

🤗 > To learn more, visit the app page or the respective model pages.
Ujjwal-Tyagi 
posted an update about 2 months ago
view post
Post
313
This is the best set of AI and ML books and a full guide to learning machine learning from the ground up. This is my study material that I used, so I thought it would be helpful to share it with others. Like, share, and add it to your collection at Ujjwal-Tyagi/ai-ml-foundations-book-collection.
prithivMLmods 
posted an update about 2 months ago
view post
Post
1925
Now, a collection of various compression schemes for Qwen3.6 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. 👇

🔗 Qwen3.6-MoE: https://huggingface.co/collections/prithivMLmods/qwen36-35b-a3b-compressions
🔗 Qwen3.6-27B Compressions: https://huggingface.co/collections/prithivMLmods/qwen36-27b-compressions

🤗 > To learn more, visit the app page or the respective model pages.