Skill Claude CodeCodex
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.
2 3d ago A 27 tokens
original MIT
2Stars on the repository
57Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained gen...
2 3d ago A 39 tokens
copy · 92% MIT
research-hqq
51Skill Claude CodeCodex
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deplo...
2 3d ago A 48 tokens
copy · 97% MIT
Skill Claude CodeCodex
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alig...
2 3d ago A 52 tokens
copy · 95% MIT
Skill Claude CodeCodex
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle...
2 3d ago A 39 tokens
copy · 97% MIT
Skill Claude CodeCodex
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-sour...
2 3d ago A 39 tokens
original MIT