Open-Weight Models Under Creative Commons Attribution-NonCommercial 4.0

static quants of https://huggingface.co/shreyansh12183/Shreyansh-STEM-AI-7B-Final For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some…

Release package for the paper's single-pass super-resolution models: Both models follow the paper protocol: RGB image → bicubic resize to 512×512 → one forward pass → mean-only color matching in the float domain, before PNG quantization: per RGB channel, clamp(sr - mean(sr,H,W) + mean(lr,H,W), 0, 1), where lr is the same 512×512 bicubic-resized tensor the model consumed. The formula is recorded in every run manifest. There is no hidden color alignment, post-processing, normalization, or implicit fallback model. The released RAESR decoder is the paper's Stage 3, seed 42, step-600 EMA checkpoint: The encoder layers are named 0-indexed in code and manifests (layers 1..23 for RAESR, layers…

Model · Speech recognition

sravaani-nepali-english-codemix-asr

AI Lab Pvt Ltd

Released by AI Lab Pvt. Ltd., Nepal. One of three models fine-tuned on the same Nepali–English code-mixed speech data: The output of every model on the test set (text only) is in Nepali speakers mix a lot of English into their speech. This model writes what they say the way people type it: Nepali in Devanagari, English words in Latin script. SraVaani-1.0 (449M parameters, hybrid TDT–CTC FastConformer) with all parameters fine-tuned. The tokenizer is unchanged. Best overall model of this release. - Nepali in Devanagari, English words in lowercase Latin script - no punctuation - numbers and symbols spelled out as words, in the language they were spoken in (ten percent or दस प्रतिशत) Held-out…

Model · Text generation

ST1.0

Sterling Ai

Hopefully the Next best SAFE agentic AI for long coding tasks. With the edition of Being better at code, less hallucination, less lies, less Confidently lies. I want to make this for the scope of a AI that offloads the coding tasks so AI can do the hard coding tasks wile the humans do stuff humans do best. As the saying something along the lines of "AI should be doing my chores wile i make art instead of me doing chores wile AI makes art" anyways I am trying to make this Model card more professional also if you want to give feedback before this moddel enteres training go on https://sterlingai.wordpress.com to awnser on how you want ai to improve. here's some planned ideas for what it mite…

Model · Text to speech

steer-tts

WhissleAI

A small English text-to-speech model that you steer with numbers. Each request can set any subset of 12 acoustic controls, for example speaking rate, loudness, median pitch, pitch range, final rise or fall, pauses, spectral tilt and breathiness. Each control is a z-score relative to the chosen voice's own neutral speech. You can also pick a style tag, give a free-text direction (which a small adapter turns into a request you can inspect), or use inline markup. The model can clone a voice from a short reference clip. The CLI looks for the model in the current directory. From anywhere else, pass it before the command (steertts --model WhissleAI/steer-tts say "Hi." -o hi.wav) or set…

Team thisray (Kaggle leaderboard name) · Author: Ssu-Rui Lee (Team Leader), RaydioTek, Taiwan · holds test/ and index/testwindows.csv. Environment: Python 3.11 and pip install -r requirements.txt; on linux-aarch64, conda-linux-aarch64.lock gives byte-identical output (see "Quick start"). One GPU, no internet access (the program disables it). Measured on the reference NVIDIA GB10: 2,016 s (S-C3) and 1,532 s (S-C6), peak GPU memory 601 MiB. The authoritative description is tartanimu-technical-report-thisray.pdf in this repository (compliance answers in Appendix B, every inference constant in Appendix F), with the organizers' starter-template team report reportthisray.md. The rest of this page…

Variante plus (CC BY-NC 4.0, solo uso no comercial): ajustada con 15 datasets, varios de licencia no permisiva o no declarada. Para uso comercial existe tde-es-en-lite-v2 (MIT). Motor de decisiones tipadas (choice / score / noul) sobre un encoder bidireccional int8 de ~42,5 M de parámetros (43 MB), recortado a español e inglés. No genera texto: elige entre opciones que le das, puntúa una rúbrica o estima si una proposición se desprende de un texto, y devuelve probabilidades, con la opción de abstenerse. Corre en CPU, 1 hilo, sin GPU y sin Python en runtime, con el binario nativo tde (Rust). Código fuente (Apache-2.0) incluido en src/; repositorio de desarrollo: typed-decision-engine.…

Model · Translation

twi-translator-gemma4-31b

Ghana NLP Community

An English-to-Twi (Akan) translation model fine-tuned on google/gemma-4-31B-it to translate English like an expert human translator. 1. Tool Calling: The model inspects the English source text, extracts key nominal terms, and emits a lookuptwitranslation tool call. 2. Offline Dictionary Lookup: The runtime looks up candidate Twi translations in an offline dictionary (478,822 English→Twi terms from SHOLA Gemini machine translations). 3. Linguistic Reasoning: The tool results are fed back into the model's thought channel (reasoningcontent), where the model reasons about morphology, syntax, and idioms. 4. Final Translation: The model outputs the accurate Twi translation, preserving the…

Model

unimate-uniml3d-f60-v3-bf16

MLX Community

UniMate (SIGGRAPH Asia 2026) generates motion from text for skeletons of any topology: animals, humanoids and rigged objects. A flow-matching transformer, conditioned on a flan-t5-base encoding of the prompt and on the skeleton's T-pose, hierarchy and joint names, turns noise into 60 frames (2 s at 30 fps) of motion. This repository holds the unimateuniml3df60v3 checkpoint converted to MLX for Apple silicon, for use with mlx-vlm. mlx-community/unimate-uniml3d-f60-v3-cross-attn-bf16 holds the full attention x cross-attention variant (unimateuniml3df60v3crossattn), converted the same way. This is an unofficial conversion, not made or endorsed by the UniMate - Extracted the EMA weights…

Model

unimate-uniml3d-f60-v3-cross-attn-bf16

MLX Community

UniMate (SIGGRAPH Asia 2026) generates motion from text for skeletons of any topology: animals, humanoids and rigged objects. A flow-matching transformer, conditioned on a flan-t5-base encoding of the prompt and on the skeleton's T-pose, hierarchy and joint names, turns noise into 60 frames (2 s at 30 fps) of motion. This repository holds the unimateuniml3df60v3crossattn checkpoint converted to MLX for Apple silicon, for use with mlx-vlm. mlx-community/unimate-uniml3d-f60-v3-bf16 holds the recommended graph attention x adaLN model (unimateuniml3df60v3), converted the same way. This is an unofficial conversion, not made or endorsed by the UniMate - Extracted the EMA weights…

License: Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (Strictly Non-Commercial / Private) Offline Deployment: Ready for 1-click GGUF quantization (< 1 GB RAM footprint under Q4KM). 1. Modern Criminal Jurisprudence: Bharatiya Nyaya Sanhita (BNS 2023), BNSS 2023, BSA 2023, electronic evidence certification (Sec 63 BSA), first-time undertrial bail (Sec 479 BNSS). 2. Financial & Tax Law: GST Input Tax Credit rules (Sec 16(2) CGST), RBI Master Directions (KYC, lending norms), SARFAESI possession procedures, IBC 2016 insolvency (Sec 7/9). 3. Multi-State Vernacular & Constitutional Rights: Landmark Supreme Court precedents (Puttaswamy privacy, Maneka Gandhi…

Developed by Vigyan AI in Varanasi, Uttar Pradesh, India. Vigyan-2B-STEM-Instruct-v1 is India's sovereign edge Small Language Model (SLM) engineered specifically for low-latency, edge-deployable STEM reasoning. At ~2.4 billion parameters, it delivers: 1. Ultra-Low VRAM Footprint: Requires only ~1.8 GB VRAM in 4-bit NF4 precision, making it deployable on consumer laptops, edge gateways, Raspberry Pi 5, and mobile devices. 2. Sub-Second Token Generation: Yields 45–60 tokens/second on a single GPU, enabling real-time interactive STEM tutoring and on-device circuit debugging. 3. Structured Tool Calling: Trained to invoke deterministic Python execution blocks ( ) for exact arithmetic…

A GGUF-quantized Mixture-of-Experts (MoE) variant of the Vigyan-7B STEM model, designed for efficient on-device inference. - For research and non-commercial use only (CC-BY-NC-4.0) - Experimental MoE architecture — use production Vigyan-7B-STEM-Instruct for stable inference If you use this model, please cite the Vigyan AI project

Developed by Vigyan AI in Varanasi, Uttar Pradesh, India. Vigyan-7B-STEM-DPO-v1 is a specialized 7-billion parameter language model trained on deep engineering and physical sciences. Unlike general-purpose foundation models that guess mathematical calculations through token auto-regression, Vigyan-7B is aligned using Direct Preference Optimization (DPO) to: 1. Eliminate Arithmetic Drift: Active negative preference margins suppress probabilistic token guessing for quantitative operations. 2. Enforce Physical Conservation Laws: Enforces physical invariant guardrails (e.g., $|\Gamma| \le 1.0$, $\eta{\text{Carnot}} 0$, $v{\text{orbit}} > 0$). 3. Structured Tool Invocations: Trained to emit…

Sovereign DARE-TIES Merged & DPO-Aligned Multi-Disciplinary SLM License: Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (Strictly Private ) Tested against 100 completely unseen frontier Ph.D. and Olympiad examination problems: 1. DARE-TIES Weight Delta Fusion: Merged 4 specialized domain LoRA adapters (phd-pure-math, silicon-rtl-eda, astro-logic, biomed-chem) into base parameters without catastrophic interference. 2. Dynamic DPO Alignment: Aligned on shreyansh12183/vigyan-gen2-7b-alignment-dataset with strict negative prompt loss masking. 3. 100% Offline Edge Ready: Quantized to Q4KM (~4.3 GB) for air-gapped workstations and defense labs.

Sovereign Direct Preference Optimization (DPO) Aligned MoE Foundation License: Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (Strictly Private ) Base Architecture: allenai/OLMoE-1B-7B-0924-Instruct (Sparse 64-Expert Top-8 Routing) 1. Contrasting Negative Prompt Gate Calibration: Router weights calibrated across 50,000 domain samples (vigyan-olmoe-master-curriculum-v1) to prevent expert cross-bleeding. 2. Selective Router Precision Guardrail: Router gating matrices (ffngateinp / gateproj) preserved at FP16/Q80 precision to eliminate token routing entropy drift. 3. High-Throughput Edge MoE: Activates only a fraction of parameters per token, delivering 7B-class…

Model · Speech recognition

X-AuT-ONNX

Mrfakename

This is an ONNX export of XPENG-AI/X-AuT, a Qwen3-ASR-0.6B model whose audio encoder was pruned from 18 to 14 layers. The files are laid out for onnxruntime-web on WebGPU. Demo: mrfakename/x-aut-webgpu. License: CC-BY-NC-4.0 (non-commercial), inherited from the original model. All credit for the model goes to XPENG-AI. This is an unofficial conversion. The decoder was built with the onnxruntime-genai builder (excludeembeds). 1. Log-mel features (Whisper-style, 128 bins, matching preprocessorconfig.json): - 16 kHz audio - nfft 400, hop 160, periodic Hann window, reflect pad - log10, clamped to max − 8, then (x + 4) / 4 - frames = len // 160 2. Encoder: run the encoder to get N audio…

Model

YahBible-Mobile

Ya'akov Yisra'el

The whole counsel of Scripture — to read, search and study, in the original Hebrew, Greek and Aramaic, on any device, offline. Free for life. Grab it first, then keep reading while it downloads. It's free — and it stays free. yes · requires payment or subscription · no. Only YahBible is fully offline — including its AI search and reasoning — and stays free with no trial or subscription. Other apps' names belong to their owners. The King James Bible with 120+ translations, verse for verse. Search however you remember a passage — "3:16 John", "the 23rd Psalm" — and switch versions without losing your place. Open any commandment in the centre: its Scripture, what it forbids, how to keep it…

Model · Text to audio

yue2-mltnt-militant-reggae

Because Reasons

Four artist-style LoRAs that push YuE2-3B into modern militant roots reggae: dark raspy male patois vocals, steppers and one-drop grooves, deep sub bass, bubbling Hammond, nyabinghi drums, horn stabs, dub sirens and spring reverb. Conscious, apocalyptic, anthemic. Each file patches both halves of YuE2 in one go: the autoregressive planner (writes the score, decides the arrangement and the vocal lines) and the flow-matching decoder (the sound). Trigger word for all three: mltnt. All demos use the same original lyric, seed 7, 32 steps dpm2 / sgmuniform, no post-processing. MLTNT Frontline — baseline recipe, prompt prompts/steppersbaseline.txt, dense lyric (verses written at ~17 words per…