Post
7
btw you might be able to game Astra usage by getting a Plus sub (obtaining Astra last), then bank the max number of resets, then upgrade to Pro at no extra cost. Maximum resets
AI & ML interests
Local LLMs
prithivMLmodsย
posted an update 8 days ago
Post
2951
ImageShield-MMCF โ Multimodal Content Filter is a multimodal content-safety classifier built on top of Qwen3.5 and is now available on Hugging Face!
This is the preview initial version (v1.0) of the model, designed to classify visual content as Safe or Unsafe, with a particular focus on detecting Non-Consensual Intimate Imagery (NCII) and other potentially sensitive visual content.
The demo is implemented in the prithivMLmods/opencaption-4b-vl-sft Space, which serves as an active content-safety layer for computer vision tasks. It helps block NCII content generation and paves the way for more meaningful and responsible creativity.
โน ImageShield-MMCF-0.8B: prithivMLmods/ImageShield-MMCF-0.8B
โน ImageShield-MMCF-2B: prithivMLmods/ImageShield-MMCF-2B
This is the preview initial version (v1.0) of the model, designed to classify visual content as Safe or Unsafe, with a particular focus on detecting Non-Consensual Intimate Imagery (NCII) and other potentially sensitive visual content.
The demo is implemented in the prithivMLmods/opencaption-4b-vl-sft Space, which serves as an active content-safety layer for computer vision tasks. It helps block NCII content generation and paves the way for more meaningful and responsible creativity.
โน ImageShield-MMCF-0.8B: prithivMLmods/ImageShield-MMCF-0.8B
โน ImageShield-MMCF-2B: prithivMLmods/ImageShield-MMCF-2B
- 2 replies
leonardlinย
posted an update 14 days ago
Post
152
I've trained an uploaded a proper MTP head for Ornith 1.5:
- head only: shisa-ai/Ornith-1.5-35B-A3B-MTP-ONLY
- full BF16: shisa-ai/Ornith-1.5-35B-A3B-MTP
- FP8: shisa-ai/Ornith-1.5-35B-A3B-MTP-FP8
- head only: shisa-ai/Ornith-1.5-35B-A3B-MTP-ONLY
- full BF16: shisa-ai/Ornith-1.5-35B-A3B-MTP
- FP8: shisa-ai/Ornith-1.5-35B-A3B-MTP-FP8
prithivMLmodsย
posted an update 17 days ago
Post
5255
The Qwen3.8 27B demo for object grounding is now available on Hugging Face Spaces.
It features three tasks: Object Detection (Bounding Boxes), Point Localization (Keypoints), and Spatial Guidance (Path Mapping).
Try it now: prithivMLmods/Qwen3.8-27B-Object-Detection
It features three tasks: Object Detection (Bounding Boxes), Point Localization (Keypoints), and Spatial Guidance (Path Mapping).
Try it now: prithivMLmods/Qwen3.8-27B-Object-Detection
Post
181
If you're into running models locally, this might be worth checking out.
https://local.ai/mahwiz/invite
https://local.ai/mahwiz/invite
Post
2101
Anthropic gave me six months of Claude Max 20x through the Claude for Open Source program, granted based on my Hugging Face work. Thank you 
Anthropic for supporting open source.
So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.
https://github.com/Nymbo/Markdown-Minimap โ issues and PRs welcome.
So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.
https://github.com/Nymbo/Markdown-Minimap โ issues and PRs welcome.
prithivMLmodsย
posted an update about 1 month ago
Post
5542
Made a demo for Text/Image-to-3D Video and Image-to-3D Video asset generation using TRELLIS.2. It is paired with Z-Image-Turbo to accelerate the input image preprocessing pipeline, streamlining the Image-to-3D workflow. The generated GLB (GL Transmission Format) files are converted into MP4 (MPEG-4) videos, making them easy to preview and share. Try it now on Hugging Face Spaces.๐ค
โ Image-to-3D-Video-Asset-Generator: prithivMLmods/Image-to-3D-Video-Asset-Generator
โ collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
โ github: https://github.com/PRITHIVSAKTHIUR/Image-to-3D-Video-Asset-Generator
โคท To learn more, visit the app page or the respective model pages.
โ Image-to-3D-Video-Asset-Generator: prithivMLmods/Image-to-3D-Video-Asset-Generator
โ collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
โ github: https://github.com/PRITHIVSAKTHIUR/Image-to-3D-Video-Asset-Generator
โคท To learn more, visit the app page or the respective model pages.
Post
5843
Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.
CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.
See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2
Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.
See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2
Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
- 6 replies
codelionย
authored a
paper about 1 month ago
codelionย
authored 3
papers about 2 months ago
pankajpandey-devย
posted an update 2 months ago
Post
4143
๐ฎ๐ณ Qwen3.5-9B Hindi Instruct โ it stops thinking in English
Ask base Qwen3.5-9B a question in Hindi and it burns hundreds of tokens thinking in English inside its think block before a single Devanagari word appears โ then code-switches in the answer. I fine-tuned it to close the think block instantly and reply in pure, native Hindi.
โ Model (16-bit): pankajpandey-dev/qwen3.5-9b-hindi-instruct
โ GGUF (Q4/Q5/Q8): pankajpandey-dev/qwen3.5-9b-hindi-instruct-GGUF
โ Try it in the browser: pankajpandey-dev/qwen3.5-9b-hindi-demo
Recipe: Unsloth + LoRA (r=16, response-only loss) on 12.9k Hindi pairs โ AI4Bharat anudesh + dolly-hi + wikiHow-hi + Aya Hindi (human-written). The Q4_K_M is 5.4 GB and runs on a plain laptop CPU.
New in this run vs my earlier models: mixed in long-form native sources (wikiHow) after my last eval showed the fine-tune traded detail for conciseness โ this one keeps answers detailed and native.
Part of my weekly ๐ฎ๐ณ Hindi LLM Series. Feedback welcome ๐
#Hindi #IndicNLP #Qwen #GGUF #LocalLLM #Unsloth
Ask base Qwen3.5-9B a question in Hindi and it burns hundreds of tokens thinking in English inside its think block before a single Devanagari word appears โ then code-switches in the answer. I fine-tuned it to close the think block instantly and reply in pure, native Hindi.
โ Model (16-bit): pankajpandey-dev/qwen3.5-9b-hindi-instruct
โ GGUF (Q4/Q5/Q8): pankajpandey-dev/qwen3.5-9b-hindi-instruct-GGUF
โ Try it in the browser: pankajpandey-dev/qwen3.5-9b-hindi-demo
Recipe: Unsloth + LoRA (r=16, response-only loss) on 12.9k Hindi pairs โ AI4Bharat anudesh + dolly-hi + wikiHow-hi + Aya Hindi (human-written). The Q4_K_M is 5.4 GB and runs on a plain laptop CPU.
New in this run vs my earlier models: mixed in long-form native sources (wikiHow) after my last eval showed the fine-tune traded detail for conciseness โ this one keeps answers detailed and native.
Part of my weekly ๐ฎ๐ณ Hindi LLM Series. Feedback welcome ๐
#Hindi #IndicNLP #Qwen #GGUF #LocalLLM #Unsloth
- 4 replies
Post
605
SPROG-9M โ a 9.37M parameter model trained from scratch to solve GSM8K-style math without using an LLM at inference.
The model, codelion/sprog-9m, predicts symbolic programs over number slots, then a deterministic executor does the arithmetic. With a simple verifier, it reaches ~11.8% on GSM8K test.
We also released the dataset: codelion/gsm8k-synth, 117K validated synthetic GSM8K-style problems.
Tiny model, no pretraining, no LLM at inference, runs on a laptop.
The model, codelion/sprog-9m, predicts symbolic programs over number slots, then a deterministic executor does the arithmetic. With a simple verifier, it reaches ~11.8% on GSM8K test.
We also released the dataset: codelion/gsm8k-synth, 117K validated synthetic GSM8K-style problems.
Tiny model, no pretraining, no LLM at inference, runs on a laptop.
pankajpandey-devย
posted an update 2 months ago
Post
7853
๐ฎ๐ณ New in my Hindi LLM Series: Gemma-4 E4B, fine-tuned for Hindi โ and it runs on your laptop's CPU.
I fine-tuned Google's new Gemma-4 E4B on ~10k Hindi instruction pairs (AI4Bharat: anudesh + dolly) using Unsloth + LoRA, on a single L4 GPU.
Then I ran an honest side-by-side eval: base Gemma-4 vs my fine-tune, across 25 Hindi prompts. The results were interesting ๐
โ My fine-tune is more concise โ ask for "3 tips" and it gives exactly 3. Base writes a 1,200-character essay.
โ Pure native Hindi โ base keeps slipping into English ("เคธเคเคคเฅเคฒเคฟเคค เคเคนเคพเคฐ (Eat a Balanced Diet)", "เคคเคพเคฐเคพ (Star)"). My fine-tune stays in clean Hindi.
โ Tighter instruction-following โ ask for a "short message" and it gives one, not a menu of options.
โ๏ธ And to be honest: base Gemma-4 is more detailed and comprehensive. I didn't build a "smarter" model โ I built a focused, Hindi-native, edge-friendly one that runs as a 5GB GGUF (Q4) on CPU.
๐ Try it:
Live demo (CPU): pankajpandey-dev/gemma-4-e4b-hindi-demo
GGUF (Ollama/llama.cpp): pankajpandey-dev/gemma-4-e4b-hindi-instruct-GGUF
16-bit model: pankajpandey-dev/gemma-4-e4b-hindi-instruct
Built with @unsloth ยท Data by @ai4bharat ๐
#Hindi #LLM #Gemma #Unsloth #IndicNLP #GGUF
I fine-tuned Google's new Gemma-4 E4B on ~10k Hindi instruction pairs (AI4Bharat: anudesh + dolly) using Unsloth + LoRA, on a single L4 GPU.
Then I ran an honest side-by-side eval: base Gemma-4 vs my fine-tune, across 25 Hindi prompts. The results were interesting ๐
โ My fine-tune is more concise โ ask for "3 tips" and it gives exactly 3. Base writes a 1,200-character essay.
โ Pure native Hindi โ base keeps slipping into English ("เคธเคเคคเฅเคฒเคฟเคค เคเคนเคพเคฐ (Eat a Balanced Diet)", "เคคเคพเคฐเคพ (Star)"). My fine-tune stays in clean Hindi.
โ Tighter instruction-following โ ask for a "short message" and it gives one, not a menu of options.
โ๏ธ And to be honest: base Gemma-4 is more detailed and comprehensive. I didn't build a "smarter" model โ I built a focused, Hindi-native, edge-friendly one that runs as a 5GB GGUF (Q4) on CPU.
๐ Try it:
Live demo (CPU): pankajpandey-dev/gemma-4-e4b-hindi-demo
GGUF (Ollama/llama.cpp): pankajpandey-dev/gemma-4-e4b-hindi-instruct-GGUF
16-bit model: pankajpandey-dev/gemma-4-e4b-hindi-instruct
Built with @unsloth ยท Data by @ai4bharat ๐
#Hindi #LLM #Gemma #Unsloth #IndicNLP #GGUF
- 12 replies
eienmojikiย
posted an update 2 months ago
Post
288
Hi everyone,
I've created a Gradio space for embedding and extracting invisible watermarks in images:
๐ eienmojiki/blind-watermark-studio
It supports hiding text, images, and bit arrays using the DWT-DCT-SVD algorithm.
Credits:
- Original library: https://github.com/guofei9987/blind_watermark
- Author: Guo Fei
:).
I've created a Gradio space for embedding and extracting invisible watermarks in images:
๐ eienmojiki/blind-watermark-studio
It supports hiding text, images, and bit arrays using the DWT-DCT-SVD algorithm.
Credits:
- Original library: https://github.com/guofei9987/blind_watermark
- Author: Guo Fei
:).
prithivMLmodsย
posted an update 3 months ago
Post
7966
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.๐
โ wan2.2-i2v-fast : prithivMLmods/Wan2.2-Fast
โ github: https://github.com/prithivsakthiur/wan2.2-i2v-fast
โ collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
โคท To learn more, visit the app page or the respective model pages.
โ wan2.2-i2v-fast : prithivMLmods/Wan2.2-Fast
โ github: https://github.com/prithivsakthiur/wan2.2-i2v-fast
โ collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
โคท To learn more, visit the app page or the respective model pages.
Post
6337
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 โ 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 โ 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.
Read online: https://datawhalechina.github.io/learning-terrain/
I wrote an open-source monograph on learning dynamics โ 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 โ 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
OzTianluย
authored a
paper 3 months ago
OzTianluย
submitted a
paper to Daily Papers 3 months ago