Tag
Explore by tags
A 3B-parameter causal LLM tuned for verifiable multi-step reasoning in math, coding and STEM using a Spectrum-to-Signal post-training pipeline (SFT, RL, offline self-distillation); not recommended for tool-calling/agent tasks.
A JSON dataset of ~1.1M anonymized coding-assistant instruction→response interactions for training and evaluating code-generation and instruction-following models; packaged for use with pandas/polars and sized at ~459 MB.
Moves repository search into a dedicated exploration subagent that issues parallel read-only READ/GLOB/GREP calls and returns compact file:line citations. Trained (4B–30B) with SFT+RL, it reduces main-agent token use up to ~60% and raises end-to-end success by up to ~5.5%.
A JSON-format text dataset of 'vibe-coding' prompt–response examples sized in the 1M–10M category. Packaged for Hugging Face Datasets with pandas/polars-ready structure; useful for fine-tuning or evaluation but lacks an explicit license and detailed provenance.
Provides 4,659 agentic single-turn SFT training pairs extracted from Claude Fable‑5, formatted as a single-column parquet for Qwen-style fine-tuning. Includes explicit chain-of-thought (<think>) blocks, XML-serialized <tool_use> calls, PII redaction, and AGPL-3.0 licensing.
Provides an open-weight native multimodal agent that understands text and images within a 1,048,576-token context window for long-horizon coding, visual reasoning, and tool-driven workflows. Uses a 2.8T-parameter Mixture-of-Experts architecture (KDA + AttnRes) with MXFP4 quantization; best suited for research and large-scale inference setups.
A collection of 953 JSON-formatted Fable 5 interaction traces (includes chain-of-thought entries), published on Hugging Face under AGPL-3.0 — meant for fine-tuning or analyzing LLM behavior but subject to license and provenance constraints.
Open-weights agentic coding model that layers Claude Fable‑5 tool‑use SFT onto a reasoning‑distilled Qwen3.6 base; emits <tool_use> XML for file edits, shell commands and reads when prompted as an agent. Designed for agentic coding workflows; AGPL‑3.0 licensed.
Provides a lightweight repository-exploration subagent for LLM coding agents: invoked on demand to run parallel read-only READ/GLOB/GREP calls and return compact file-path plus line-range citations so the main solver gets focused evidence instead of noisy reads.
Frames AI research as a trainable practice of reading, building, debugging, and fast feedback. The essay is most useful for researchers learning how to avoid hype-chasing, benchmark tunnel vision, and agent-induced blind spots.
Fine-tuned full checkpoint of the Qwen3.6-27B base that produces structured, trace-style assistant outputs for code, technical reasoning, and instruction-following. Packaged for local GGUF conversion and local inference; not a LoRA adapter and not validated for production use.
Provides a large language model optimized for long-horizon agentic tasks and end-to-end coding workflows — with a stable 1,000,000-token context, IndexShare sparse-attention and multi-level thinking-effort modes. MIT-licensed and designed for deployments that need sustained long-context reasoning and coding.