AI & ML interests

Small LMs for small computers

Recent Activity

prithivMLmodsย 
posted an update 2 days ago
mmhamdyย 
posted an update 4 days ago
view post
Post
94
Things rarely go as we expect!

In 2017, Google released the Transformer architecture. While it was clear the model was promising, absolutely no one (including its authors) anticipated the pervasive global revolution it would create!

The authors actually viewed the Transformer as just a stepping stone for a much more ambitious project: The MultiModel.

Their ultimate goal was to build a single deep learning architecture capable of jointly learning massive, diverse tasks across entirely different domains (in 2017). A One Model To Learn Them All.

In fact, the MultiModel paper was published in the exact same month as Attention Is All You Need!

But history had other plans. The building block eclipsed the grand design!

So, have you heard about the MultiModel before? ๐Ÿ˜€
  • 1 reply
ยท
prithivMLmodsย 
posted an update 5 days ago
view post
Post
6045
PiD โ€” 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!

๐Ÿค— Space: prithivMLmods/PiD-Image-Upscaler
๐Ÿ”— Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

๐Ÿค— > To learn more, visit the app page or the respective model pages.
Locutusqueย 
posted an update 8 days ago
view post
Post
195
๐Ÿš€ Introducing Esmeralda-Llama-3.1-8B-control
The first release in the Esmeralda model family by Locutusque.

This model is intentionally small and experimental โ€” a control/baseline proof-of-concept designed to answer one question:

ยซโ€œHow strong is my new "Locutusque/esmeralda-agentic" dataset before scaling to larger runs?โ€ยป

Training Details

- Base: Llama 3.1 8B
- Training precision: bf16 mixed precision
- Chat template: modified ChatML
- Dataset size: ~37k examples
- Examples actually used for this run: ~5k

The dataset includes:

- multi-turn agentic traces
- reasoning traces
- structured assistant behavior
- generalist instruction data

Benchmark Results

Compared against:

- Llama 3.1 8B Instruct
- Hermes-3-Llama-3.1-8B

HumanEval

57.3 โ€” Esmeralda
56.1 โ€” Llama 3.1 Instruct
52.4 โ€” Hermes-3

MBPP

53.2 โ€” Esmeralda
56.8 โ€” Llama 3.1 Instruct
48.2 โ€” Hermes-3

GPQA Diamond

15.7 โ€” Esmeralda
15.7 โ€” Llama 3.1 Instruct
18.2 โ€” Hermes-3

EQ-Bench

59.2 โ€” Esmeralda
61.1 โ€” Llama 3.1 Instruct
63.1 โ€” Hermes-3

EQ-Bench Parseable (Syntax Stability)

๐Ÿ”ฅ 100.0% โ€” Esmeralda
92.4% โ€” Llama 3.1 Instruct
91.2% โ€” Hermes-3

Here Be Dragons ๐Ÿ‰

I also experimented with a new TruthfulQA free-generation evaluation setup.

- Responses were judged by Gemma 4 26B A4B
- The judge compared generations directly against ground-truth answers
- Models were evaluated in 8-bit quantized form to speed up inference

TruthfulQA (LLM Judge)

0.682 โ€” Esmeralda-Llama-3.1-8B-control
0.587 โ€” Hermes-3-Llama-3.1-8B (reported MC2 score; methodology differs)

For a lightweight control run trained on only a fraction of the dataset, Iโ€™m pretty encouraged by the results.

The model is released under the standard Llama 3.1 license, and Iโ€™d genuinely love feedback from people testing it in real workflows.

Model: Locutusque/Esmeralda-Llama-3.1-8B-control

Dataset: Locutusque/esmeralda-agentic

prithivMLmodsย 
posted an update 11 days ago
view post
Post
5533
I've made 8 Spaces in the Qwen-Image-Edit series, and out of them, 5 Spaces reached โ€œSpace of the Weekโ€! 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! ๐Ÿค—โค๏ธ

๐Ÿ”— Spaces: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
  • 4 replies
ยท
Tonicย 
posted an update 19 days ago
view post
Post
2789
๐Ÿ™‹๐Ÿปโ€โ™‚๏ธ Hey there folks ,

Turns out : if we predict ๐ŸŒ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.

Sentinel-2 imagery ๐Ÿ›ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.

meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐Ÿ“กearth-bound response .

I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.

At least that's the concept !

check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth


- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
  • 2 replies
ยท
ajibawa-2023ย 
posted an update 27 days ago
view post
Post
2106
Stitched-Reasoning-Trajectories-7M

Dataset: ajibawa-2023/Stitched-Reasoning-Trajectories-7M
Stitched-Reasoning-Trajectories-7M is a massive-scale, synthetic multi-hop reasoning dataset. It was built by algorithmically "stitching" together discrete reasoning traces from the original glaiveai/reasoning-v1-20m dataset into continuous, coherent, and logically structured multi-agent trajectories.

By extracting internal sub-questions from <think> blocks and mapping high-information keyword overlaps, this dataset transforms single-turn Q&A pairs into deep, multi-step research plans. To ensure high quality and eliminate "topic drift," every trajectory has been verified using a dense semantic embedding model (BAAI/bge-large-en-v1.5).

The resulting dataset consists of 709 .jsonl files containing over 7.2 million entirely deduplicated, highly coherent reasoning chains.
Sri-Vigneshwar-DJย 
posted an update about 1 month ago
view post
Post
144
![Feather DB LongMemEval Results]( Hawky-ai/longmemeval-results)

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

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

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

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

pip install feather-db

Raw results + audit JSONs: Hawky-ai/longmemeval-results
prithivMLmodsย 
posted an update about 1 month ago
view post
Post
5922
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.

๐Ÿค— Demo: prithivMLmods/Multimodal-Edge-Node
๐Ÿ”— GitHub: https://github.com/PRITHIVSAKTHIUR/Multimodal-Edge-Node
โœ… Multimodal Apps Collections: https://huggingface.co/collections/prithivMLmods/hall-of-multimodal-apps

๐Ÿค— > To learn more, visit the app page or the respective model pages.
Tonicย 
posted an update about 1 month ago
view post
Post
4287
๐Ÿ™‹๐Ÿปโ€โ™‚๏ธ Hey there folks,

since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !

Check this one out :
NuTonic/sat-bbox-metadata-sft-v1

the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .

hope you like it ! ๐Ÿš€
  • 2 replies
ยท
Tonicย 
posted an update about 1 month ago
view post
Post
3636
๐Ÿ™‹๐Ÿปโ€โ™‚๏ธ Hey there folks ,

I'm sharing huggingface's largest dataset of annotated statelite images today.

check it out here : NuTonic/sat-image-boundingbox-sft-full

I hope you like it , the idea is to be able to use this with small vision models ๐Ÿš€
prithivMLmodsย 
posted an update about 1 month ago
view post
Post
1913
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. ๐Ÿ‘‡

๐Ÿ”— Qwen3.6-MoE: https://huggingface.co/collections/prithivMLmods/qwen36-35b-a3b-compressions
๐Ÿ”— Qwen3.6-27B Compressions: https://huggingface.co/collections/prithivMLmods/qwen36-27b-compressions

๐Ÿค— > To learn more, visit the app page or the respective model pages.
ajibawa-2023ย 
posted an update about 1 month ago
view post
Post
1305
Ruby-Code-Large
Dataset : ajibawa-2023/Ruby-Code-Large

Ruby-Code-Large is a large-scale corpus of Ruby programming language source code comprising 331,743 code samples stored in .jsonl format. The dataset is designed to support research and development in large language model (LLM) pretraining, static analysis, web application development, and software engineering automation within the Ruby ecosystem.

By offering a substantial, language-focused dataset, Ruby-Code-Large enables targeted experimentation in dynamic programming, object-oriented design, and rapid application developmentโ€”areas where Ruby is widely used, particularly in web frameworks and scripting.

Ruby-Code-Large addresses the lack of large, curated, Ruby-specific datasets, enabling focused research on expressive syntax, metaprogramming, and high-level abstractions.
ajibawa-2023ย 
posted an update about 1 month ago
view post
Post
6114
Go-Code-Large
Dataset: ajibawa-2023/Go-Code-Large

Go-Code-Large is a large-scale corpus of Go (Golang) programming language source code, comprising 316,427 code samples stored in .jsonl format. The dataset is designed to support research and development in large language model (LLM) pretraining, static analysis, cloud-native systems, and modern backend software engineering.

By offering a focused and curated dataset for Go, this corpus enables experimentation in concurrent programming, distributed systems, and performance-oriented backend servicesโ€”domains where Go is widely adopted.

Go-Code-Large addresses the relative scarcity of large, language-specific datasets for Go, enabling targeted research into idiomatic Go patterns, concurrency primitives, and scalable system design.
  • 2 replies
ยท
prithivMLmodsย 
posted an update about 2 months ago
view post
Post
4211
HY-World-2.0 โ€” A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds is now available on Spaces, and it works both as native Gradio components and in Gradio server mode.

> HY-World-2.0-Demo: prithivMLmods/HY-World-2.0-Demo
> HY-World-2.0 [Server Mode]: prithivMLmods/HY-World-2.0-Demo
> Featuring 3D reconstruction and Gaussian splats with the Rerun viewer, along with camera poses, depth maps, and surface normals.
> In Server Mode, Gradio is served via FastAPI, with FastAPI remaining the top-level server.
> Model: tencent/HY-World-2.0
> GitHub: https://github.com/PRITHIVSAKTHIUR/HY-World-2.0-Demo

๐Ÿค—To learn more, visit the app page or the respective model pages.
prithivMLmodsย 
posted an update about 2 months ago
view post
Post
6232
A new comparator on Spaces showcases Standard FLUX.2 Decoder vs. FLUX.2 Small Decoder. The Small Decoder is ~1.4ร— faster, uses ~1.4ร— less VRAM, and maintains near-identical image quality. It has ~28M parameters with narrower channels [96, 192, 384, 384] vs. [128, 256, 512, 512], and the demo supports sequence generation by running both decoders simultaneously and comparing the results side by side.

๐Ÿค— Comparator: https://huggingface.co/spaces/prithivMLmods/Flux.2-4B-Decoder-Comparator
๐Ÿ”— FLUX.2-small-decoder: black-forest-labs/FLUX.2-small-decoder
๐Ÿ”— GitHub: https://github.com/PRITHIVSAKTHIUR/Flux.2-4B-Encoder-Comparator
๐Ÿš Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

๐Ÿค— > App built on the Gradio SDK. To learn more, visit the app page or the respective model pages.
prithivMLmodsย 
posted an update about 2 months ago
view post
Post
4251
Now, a collection of various compression schemes for Gemma 4 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. ๐Ÿ‘‡

๐Ÿ”—Gemma 4 Compression(s)- https://huggingface.co/collections/prithivMLmods/gemma-4-compressions
๐Ÿ”—Gemma 4 Uncensored [MAX] + Compression(s) - [`ฮฒ ]- https://huggingface.co/collections/prithivMLmods/gemma-4-uncensored-max-compressions
๐Ÿ”—Gemma 4 Compression(s) - MoE- https://huggingface.co/collections/prithivMLmods/gemma-4-compressions-moe
๐Ÿ”—Gemma-4 F32 GGUF- https://huggingface.co/collections/prithivMLmods/gemma-4-f32-gguf

๐Ÿค— > To learn more, visit the app page or the respective model pages.