davila7/claude-code-templates
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…
Installation
npx skills add https://github.com/davila7/claude-code-templates
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for pref…
50 installsTop-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, …
2.3K installsTechniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP inp…
1.9K installsUse when adding, modifying, optimizing, or debugging CuTile autotuning code.
1.5K installsChange the sync configuration of an existing data warehouse schema — switch sync_type, pick a d…
2 installsOptimize vector index performance for latency, recall, and memory. Use when tuning HNSW paramet…
26 installsAlso in this package
Other skills from davila7/claude-code-templates · top by installs.
npx skills add https://github.com/davila7/claude-code-templates
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Repository health
main
Skill metadata
Parsed from SKILL.md frontmatter.
History
- First seen on skills.sh
- First recorded snapshot · 382 installs