Open-Weight Models

Model · Image and text to text

ViSkill-Sokoban

Hongxing Li

This repository contains ViSkill-Sokoban and its visual skill library, introduced in ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills. ViSkill-Sokoban is a visual agent model for Sokoban, built upon Qwen2.5-VL-3B-Instruct. It represents successful interactions as reusable visual skill cards. Geometry-aware retrieval guides the agent, while PPO with skill-guided rewards and online skill distillation jointly improve the policy and skill library. Model files are stored at the repository root, with the accompanying visual skill library in skilllibrary/. For the full ViSkill agent pipeline, including skill retrieval and environment interaction, please refer to our code…

Model · Speech recognition

VibeVoice-ASR-AWQ-W4A16-ASYM-DFlash2

Nikita Davidchuk

VibeVoice-ASR (7B), AWQ W4A16 (asymmetric, groups of 128), with its DFlash 2 drafter bundled in drafter/: one download, and vibevoice.c decodes with speculative decoding -- the drafter proposes 8 tokens in one pass, the model checks them in one pass and keeps the ones it agrees with. the model's own decode step, so the transcript is byte-for-byte the one without the drafter. (With a drafter vibevoice.c attends with flashinfer, which checks rows together; the transcript is then --attn flashinfer's.) Needs vibevoice.c with DFlash 2 support: branch dflash2 (PR #48), in the next release. A model directory's drafter/ is used without asking: vibevoice.c b72be15 (branch dflash2), RTX 3090, greedy…

Model · Speech recognition

VibeVoice-ASR-DFlash2

Nikita Davidchuk

VibeVoice-ASR (7B), the original BF16 weights as Microsoft published them, with its DFlash 2 drafter bundled in drafter/: one download, and vibevoice.c decodes with speculative decoding -- the drafter proposes 8 tokens in one pass, the model checks them in one pass and keeps the ones it agrees with. the model's own decode step, so the transcript is byte-for-byte the one without the drafter. (With a drafter vibevoice.c attends with flashinfer, which checks rows together; the transcript is then --attn flashinfer's.) Needs vibevoice.c with DFlash 2 support: branch dflash2 (PR #48), in the next release. A model directory's drafter/ is used without asking: vibevoice.c runs BF16 weights as dense…

Model · Speech recognition

VibeVoice-ASR-DFlash2-Drafter

Nikita Davidchuk

A DFlash 2 block drafter for VibeVoice-ASR (7B) (Ar4ikov/VibeVoice-ASR-AWQ-W4A16-ASYM), for speculative decoding in vibevoice.c. It proposes 8 tokens in one pass; vibevoice.c checks them in one pass of the model and keeps the ones the model agrees with, plus one of its own. the model's own one-token decode step, so the transcript with this drafter is byte-for-byte the transcript without it — words, timestamps, speakers. The drafter only changes how many passes it takes. One thing changes with --draft: vibevoice.c then attends with flashinfer (--attn auto picks it), because flashinfer checks several rows in one pass over the cache where the default fa2 walks it once per row. The transcript…

Model · Speech recognition

VibeVoice-ASR-DFlash2-Drafter-AWQ-W4A16-ASYM

Nikita Davidchuk

A DFlash 2 block drafter for VibeVoice-ASR (7B) (Ar4ikov/VibeVoice-ASR-AWQ-W4A16-ASYM), for speculative decoding in vibevoice.c. It proposes 8 tokens in one pass; vibevoice.c checks them in one pass of the model and keeps the ones the model agrees with, plus one of its own. the model's own one-token decode step, so the transcript with this drafter is byte-for-byte the transcript without it — words, timestamps, speakers. The drafter only changes how many passes it takes. One thing changes with --draft: vibevoice.c then attends with flashinfer (--attn auto picks it), because flashinfer checks several rows in one pass over the cache where the default fa2 walks it once per row. The transcript…

Working checkpoints from a Canadian fine-tune of Victoria; not a release.

Runtime assets use neutral filenames. This is an application package; underlying components retain their original licenses and authorship.

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…

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…

Vigyan Pro is a private, 100% offline AI and interactive 3D science studio built at ExperimentLab.in for engineers, students, and researchers. - 3D Models & Design (/cad3d): Inspect interactive 3D gears, molecules, and structures directly inside your conversation. - Math & Graphs (/plot, /mathvisual, /derive): Plot functions, visualize 3D surfaces, and solve equations step-by-step. - Physics & Circuits (/simulate, /circuit, /semiconductor): Run live motion, orbital, and electronic circuit simulations at 60 FPS. - Science & Biology (/biology, /material, /medical): Explore 3D DNA double helices, crystal lattices, and clinical biomarker panels. - Smart GPU + CPU Hybrid Engine: Automatically…

static quants of https://huggingface.co/simpledirect/Vinci-Cyber-30B-1.0 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 lower-quality…

weighted/imatrix quants of https://huggingface.co/simpledirect/Vinci-MLE-8B-1.0 For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Vinci-MLE-8B-1.0-GGUF 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 lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…

Model · Text generation

Viu-1.5B-MoE

Vipin Kumar

Viu-1.5B-MoE is a sovereign Indian Large Language Model featuring a 48-Layer Ultra-Deep Frontier Mixture of Experts (MoE) architecture designed for deep hierarchical reasoning, Indic multilingual fluency (Hindi, Hinglish, English), and high-speed on-device inference. 1. 48-Layer Ultra-Deep Reasoning: Deep hierarchical abstraction across 4 cognitive tiers (12 layers each: Token Mechanics $\rightarrow$ Multilingual Alignment $\rightarrow$ Domain Knowledge $\rightarrow$ Deep Deductive Logic). 2. Compressed Sparse Attention 2 (CSA2): DeepSeek-V4.1 style low-rank KV compression saving 80% KV-cache memory for long-context inference on consumer GPUs. 3. Manifold-Constrained Hyper-Connections…

Model · Text generation

ViuMini-MoE-242M

Vipin Kumar

Viu-1.5B-MoE is a sovereign Indian Large Language Model featuring a 48-Layer Ultra-Deep Frontier Mixture of Experts (MoE) architecture designed for deep hierarchical reasoning, Indic multilingual fluency (Hindi, Hinglish, English), and high-speed on-device inference. 1. 48-Layer Ultra-Deep Reasoning: Deep hierarchical abstraction across 4 cognitive tiers (12 layers each: Token Mechanics $\rightarrow$ Multilingual Alignment $\rightarrow$ Domain Knowledge $\rightarrow$ Deep Deductive Logic). 2. Compressed Sparse Attention 2 (CSA2): DeepSeek-V4.1 style low-rank KV compression saving 80% KV-cache memory for long-context inference on consumer GPUs. 3. Manifold-Constrained Hyper-Connections…