Discover the Best AI Resources

Laguna XS.2

A 33B Mixture-of-Experts text-to-text model optimized for local, long-context agentic coding—3B activated params per token, 131k token window, mixed sliding-window and global attention, FP8 KV cache, Apache-2.0 license.

NU-TONIC raw SFT Full

Provides satellite image tiles paired with per-tile land-cover captions and bounding-box overlays in SFT-compatible JSONL for supervised fine-tuning. Includes RGB chips, optional Mapbox context, metadata, and train/validation/test splits derived from Sentinel‑2 and Earth Engine labels.

Gemma 4 E4B-it Assistant

Provides a lightweight assistant (draft) model for Gemma 4 E4B used in speculative-decoding pipelines — it predicts token drafts that the target model verifies in parallel, enabling up to ~2× decoding speedups while preserving identical final outputs. Useful for low-latency, multimodal assistant and on-device scenarios.

LTX2.3-ICEdit-Insight

Performs task-aware generative video restoration and editing in latent video space — restoration, super-resolution, watermark and subtitle removal — adapting LTX‑2.3 with IC‑Edit/IC‑LoRA adapters to prioritize temporal consistency and occlusion-aware reconstruction.

google/gemma-4-31B-it-assistant

A lightweight 'drafter' assistant for Gemma 4 31B that generates speculative token drafts to enable up-to-2× decoding speedups while preserving final output quality; compatible with Hugging Face Transformers and any-to-any pipelines.

Agent Toolkit for AWS

Provides a single MCP endpoint that lets AI coding agents search AWS docs, run sandboxed Python scripts, and make authenticated AWS API calls with enterprise guardrails like IAM condition keys, CloudWatch metrics, and CloudTrail auditing.

google/gemma-4-26B-A4B-it-assistant

Acts as the assistant (drafter) checkpoint for Gemma 4 26B A4B on Hugging Face, used in Speculative Decoding to pre-draft tokens and speed up generation. Designed for long-context, multimodal workflows where lower latency and on-device or edge inference matter.

Future AGI

Provides an end-to-end platform to evaluate, observe, protect, and optimize LLM and AI agent deployments. Integrates OpenTelemetry tracing, 50+ evaluation metrics, agent simulations, an OpenAI‑compatible gateway, and guardrails; self‑hostable under Apache 2.0.

NVIDIA Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

Unifies video, audio, image and text understanding for enterprise Q&A, summarization, transcription and document intelligence. The NVFP4 quantized variant reduces footprint to ~20.9GB for more efficient single‑GPU deployment and is tuned for NVIDIA runtimes (vLLM, TensorRT).

DeepSeek-V4-Distill-8100x

Supervised fine-tuning dataset of 7,716 reasoning-focused Q&A examples distilled from the DeepSeek‑V4‑Flash teacher; provided as a cleaned JSONL train split for distillation and SFT experiments.

Deepseek-v4-pro-max-distill-1000x

1,000 JSONL samples containing full chain-of-thought reasoning traces and final answers produced by DeepSeek‑V4‑Pro for use in student-model distillation and quality checks. Prompts sampled from Jackrong/GLM-5.1-Reasoning-1M-Cleaned; Apache‑2.0 licensed.

SALT-NLP/SWE-chat

Collects real-world developer–AI coding sessions with full transcripts, tool calls, agent thinking traces, Git commits, and agent vs. human code attribution. Packaged as Parquet tables (conversations, sessions, commits, checkpoints, repositories) for analysis of agent behavior and human–AI collaboration.