Tag

ADHD — a skill for coding agents

Spawns parallel, isolated LLM reasoning frames, then scores, clusters and prunes ideas to avoid premature convergence. Packaged as a reusable Claude/Codex agent skill with CLI and TypeScript APIs for ideation, design decisions and fuzzy debugging.

Scaffold-CoT

Provides ~3.8M chain-of-thought training examples (~3B tokens) that use a fixed 'Inventory / Interaction / Execution' scaffold to improve concise, reliable reasoning in small LLMs; topic-labeled, deduped, includes real tool-execution traces, CC-BY-4.0.

The Open Distillation Codex

Provides 16M+ instruction–response samples and ~81 GB (7,090 compressed GitHub repos) distilled from 68 open-source sources, organized into 8 categories for SFT, coding agents and reasoning research. Model-generated content; released as a curated MIT-licensed collection.

Bonsai 27B (1-bit)

Runs a full 27B-class language model using end-to-end binary (1.125-bit) weights, cutting FP16 size to ~3.9 GB. Key features: 262k-token context, custom 1-bit kernels for Apple MLX and CUDA, and an optional DSpark drafter for faster decoding. Best when memory footprint matters; trades some FP16 accuracy for on-device feasibility.

Ternary Bonsai 27B — GGUF

Provides a 27B-class Qwen3.6-derived language model in GGUF with end-to-end ternary weights (Q2_0_g128), reducing deployed footprint to ~7.2 GB while retaining ~95% of FP16 reasoning ability and enabling on-device 262K-token context inference.

Bonsai-27B-gguf

Runs a full 27B-class Qwen3.6-derived language model in a ~3.9 GB 1-bit GGUF pack for on-device inference with a 262K-token context; true 1.125 bits/weight binary representation, DSpark speculative drafter, and llama.cpp (CUDA/Metal/CPU) support.

Ternary Bonsai 27B (prism-ml/Ternary-Bonsai-27B-mlx-2bit)

Runs a full 27B-class Qwen3.6-derived LLM in a ~7.2 GB ternary/2‑bit format for on-device or single‑GPU text generation, retaining ~95% of FP16 performance and supporting a 262K‑token context. Designed for laptop/GPU deployment; exceeds typical phone memory limits.

Weak-to-Strong Generalization via Direct On-Policy Distillation

Transfers RL-induced policy shifts from a smaller 'weak' teacher to a stronger target by using the teacher's post-/pre-RL log-ratio as a dense implicit reward applied on the student's on-policy states. Enables reuse of RL supervision without running RL rollouts on the target, improving sample/time efficiency.

Reasoning Corpus 5M

Provides ~5M model-generated reasoning chains (within 5k sequence length) with structured fields for supervised fine-tuning, reasoning distillation, and instruction tuning. Includes separate fields for prompt, reasoning trace, final answer and a ChatML view; streaming access recommended for large-scale use.

Reasoning Corpus 5M

Provides ~5M tokens of chain-of-thought reasoning traces generated by many LLMs (DeepSeek, Qwen, Gemma, etc.) for training and evaluating reasoning SLMs — includes repo_id, tok_len, user, thought_trace, assistant and ChatML fields; sequences limited to 5k.

Blood Pathology LIMS Environment

Simulates a hospital LIMS to benchmark agentic clinical reasoning: agents inspect demographics, medications, lab orders/results and then submit ICD‑10 diagnostic reports scored by deterministic, context‑aware graders. Ships as an OpenEnv/FastAPI runtime with 8 scenarios, step‑level rewards and trajectory capture for RL, tool‑use and evaluation.

Digital Hospital Environment

Evaluates agents inside a structured hospital workflow via a downloadable FastAPI runtime that enforces role-specific tool permissions, evidence-before-treatment discipline, deterministic grading, dense process rewards, and full trajectory logging. Designed for RL, offline policy learning, multi-agent workflow research and process-supervision datasets; not for real patient care.