Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
pankajpandey-dev 
posted an update 1 day ago
view post
Post
7382
🇮🇳 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
  • 2 replies
·
prithivMLmods 
posted an update 3 days ago
view post
Post
5917
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.
RiverRider 
posted an update 3 days ago
view post
Post
4747
SRT-introspect: Live Token-by-Token Readout of LLM Internal Reasoning

I have released SRT-introspect, a new public demonstration that makes the hidden reasoning process of a frozen large language model visible in real time.

The interface runs a Qwen-2.5-7B backbone equipped with the SRT Adapter and Activation Verbalizer. As the model generates each token, the system continuously measures divergence across attention heads, identifies high-signal moments, and translates the corresponding hidden-state object representations into natural-language verbalizations. You see exactly what the model is internally representing at the precise points where its computation is most active, complete with divergence scores, reflexivity estimates, and per-layer traces.

This is not a summary of the final output. It is a direct window into the model’s latent conceptual landscape, showing the dominant training-data attractors that activate even when the prompt asks for first-principles reasoning. The adaptive scheduler concentrates verbalizations precisely where the real internal work occurs, turning what used to be opaque black-box generation into observable, analyzable data.

The result is the clearest public demonstration yet that modern LLMs possess a rich, structured semiotic infrastructure that can now be audited without retraining or fine-tuning.

Try it:
RiverRider/srt-introspect
pankajpandey-dev 
posted an update 6 days ago
view post
Post
2614
🧬 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
ovi054 
posted an update about 7 hours ago
view post
Post
29
Color Grading Transfer⚡

ovi054/Color-Grade-Transfer-Qwen-Image

What if you could steal color grade from your favorite films or any still image and apply it to your own content. And no, you don't need to be a professional colorist.

Input 1: Source Image - Content to be preserve
Input 2: Reference Image - Any still from films
Output: Color graded output image

👉 Try it now: ovi054/Color-Grade-Transfer-Qwen-Image
prithivMLmods 
posted an update about 9 hours ago
kanaria007 
posted an update about 17 hours ago
view post
Post
72
✅ Article highlight: *Worlds as Training Substrates* (art-60-167, v0.1)

TL;DR:
This article argues that gameplay is not automatically a training dataset.

A persistent world can generate incredibly rich traces of action, conflict, coordination, failure, and recovery. But turning that into a learning corpus is a governance problem, not a data-hoarding problem. If you want to say *“Model M was trained on World W”*, you need pinned corpus manifests plus receipted extraction, consent/redaction, decontamination, and training runs.

Read:
kanaria007/agi-structural-intelligence-protocols

Why it matters:
• turns “world data” into a governed learning substrate instead of a vibes dataset
• makes provenance, canon, and performance posture part of training honesty
• prevents extraction pipelines from silently rewriting what the world was
• treats contamination, leakage, and consent as first-class training-governance issues

What’s inside:
• *training corpus manifests* that pin world identity, canon snapshot, and performance posture
• *learning trace extraction contracts* for what may be pulled from world history
• *dataset build receipts* and *training run receipts* for provenance
• *decontamination receipts* for leak prevention and train/eval hygiene
• governed rules for changing extraction or normalization surfaces without laundering history

Key idea:
Do not say:

*“we trained on gameplay data.”*

Say:

*“this model was trained on a governed corpus built from this world, under these extraction, redaction, decontamination, and training receipts.”*

That is how learning stops being data scavenging and becomes governance with receipts.
  • 2 replies
·
pankajpandey-dev 
posted an update 5 days ago
view post
Post
616
🇮🇳 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 8 days ago
view post
Post
249
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
danielhanchen 
posted an update 11 days ago
Recently active users