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
SKT AI Labs, we are pushing the boundaries of AI architecture and researchโand today, we are thrilled to open our doors to the global research community!
โWe warmly welcome researchers, developers, and AI enthusiasts to join us and contribute to our R&D efforts.
โ๐งช What You Can Explore:
We invite you to experiment with our WMF (Weight Manifold Fusion) technology. You can test this high-dimensional fusion technique on smaller models to gain a deeper understanding of its behavior and token convergence.
โIf it works: Fantastic! Share your results with us and contribute directly to the core vision of SKT AI Labs.
โIf it doesn't work: No problem at all! Your critical feedback is just as valuable to us. Every experiment and anomaly helps us refine this architecture to make it more stable and robust.
โWe firmly believe that true innovation stems from community collaboration and transparent testing. Let's build the future of advanced AI together. Your ideas, test results, and feedback are always welcome!
You Can Still Research and Development On WMF Only SKT-SURYA-H Model is Dismissed.
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:
Weโre excited to release NRS_QWEN_MYTHOS_1M โ a powerful reasoning model built on Qwen 3.5 9B! At SKT AI LABS, weโve supercharged this 9B model with our proprietary Neural Reasoning System (NRS) to deliver next-level performance.
๐ฅ Why This Model is a Game-Changer: โ 100x Reasoning Capacity โ Exceptional deep logical thinking and complex problem-solving โ 1 Million Token Context โ Perfect for massive codebases, long documents, and multi-turn agentic workflows โ Advanced Thinking Mode โ Native <think> tags for true step-by-step Chain-of-Thought reasoning โ Tool-Use Ready โ Optimized for Python execution, Web Search, and self-correction โ Blazing Fast โ Runs smoothly on consumer GPUs like RTX 3090/4090
Whether youโre a developer building coding agents, a researcher working with long-context data, or someone who loves powerful reasoning โ this model is built for you.
Shipped v0.1.2 of vtx โ a minimalist coding agent for the terminal.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono โ same principles, pure Python, no transpiled runtime.
What ships out of the box:
โ Textual TUI + headless CLI (vtx -p "fix the failing test") โ 49 LLM provider gateways, all declared in a single provider.yaml โ 5 core tools (read / edit / write / bash / find) plus web search and fetch โ Session tree with compaction, handoff, and resume โ AGENTS.md / CLAUDE.md auto-discovery โ Skills system โ drop SKILL.md files in .agents/skills/ and they become slash commands โ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE) โ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
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
๐ฎ๐ณ Gemma-3-1B Hindi Instruct โ 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. โ Fine-tune (16-bit): pankajpandey-dev/gemma-3-1b-hindi-instruct โ 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 โ 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 โ it's a lightweight/edge experiment, not a 4B replacement. Gemma-3-4B Hindi is next. Part of my Hindi LLM Series โ openly-licensed Indic models for local & edge use. Feedback welcome ๐ #Hindi #IndicNLP #GGUF #LocalLLM #Gemma #EdgeAI
Released lafzyn , built over Qwen, an Urdu language model that converts Urdu text into IPA phonetic transcription, with GGUF builds for local inference.
Release contents: - mahwizzzz/lafzyn: full weights - mahwizzzz/lafzyn-gguf: quantized builds
๐ฎ๐ณ Qwen3-4B Hindi Instruct v2 โ 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 โ so I fine-tuned Qwen3-4B on 10K Hindi instruction pairs and shipped it with a full GGUF quant ladder. โ Fine-tune (16-bit): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2 โ 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 โ fits comfortably on a laptop, CPU or GPU. Part of my Hindi LLM Series โ building openly-licensed Indic models for local and edge use. More coming (Gemma next). Feedback welcome ๐ #Hindi #IndicNLP #GGUF #LocalLLM #Qwen
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!
๐งฌ Just uploaded K-quants of Carbon-3B for llama.cpp users! @HuggingFaceBio released the original GGUF in bf16 only โ so I added the full quant ladder for CPU/edge inference: โข Q2_K โ 1.4 GB โข Q3_K_M โ 1.8 GB โข Q4_K_M โ 2.1 GB โญ โข Q5_K_M โ 2.4 GB โข Q6_K โ 2.7 GB โข Q8_0 โ 3.5 GB ๐ 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 ๐ #GGUF #llamacpp #genomics #DNA
I've made 8 Spaces in the Qwen-Image-Edit series, and out of them, 5 Spaces reached โSpace 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.
@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 !
6 Open-Source Libraries to FineTune LLMs 1. Unsloth GitHub: https://github.com/unslothai/unsloth โ Fastest way to fine-tune LLMs locally โ Optimized for low VRAM (even laptops) โ Plug-and-play with Hugging Face models
3. TRL (Transformer Reinforcement Learning) GitHub: https://github.com/huggingface/trl โ RLHF, DPO, PPO for LLM alignment โ Built on Hugging Face ecosystem โ Essential for post-training optimization
4. DeepSpeed GitHub: https://github.com/microsoft/DeepSpeed โ Train massive models efficiently โ Memory + speed optimization โ Industry standard for scaling
6. PEFT GitHub: https://github.com/huggingface/peft โ Fine-tune with minimal compute โ LoRA, adapters, prefix tuning โ Best for cost-efficient training
