llm-tuning-patterns by parcadei/continuous-claude-v3
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill llm-tuning-patterns基于 APOLLO 和 Godel-Prover 研究的、有实证依据的 LLM 参数配置模式。
不同的任务需要不同的 LLM 配置。请使用这些有实证依据的设置。
基于 APOLLO 奇偶性分析:
| 参数 | 值 | 依据 |
|---|---|---|
| max_tokens | 4096 | 证明需要空间进行思维链推理 |
| temperature | 0.6 | 更高的创造力用于策略探索 |
| top_p | 0.95 | 允许多样化的证明路径 |
在给出策略前,始终要求一个证明计划:
Given the theorem to prove:
[theorem statement]
First, write a high-level proof plan explaining your approach.
Then, suggest Lean 4 tactics to implement each step.
证明计划(思维链)能显著提高策略质量。
对于困难的证明,使用并行采样:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 参数 | 值 | 依据 |
|---|---|---|
| max_tokens | 2048 | 对大多数函数来说足够 |
| temperature | 0.2-0.4 | 倾向于确定性输出 |
| 参数 | 值 | 依据 |
|---|---|---|
| max_tokens | 4096 | 为探索提供空间 |
| temperature | 0.8-1.0 | 最大化创造力 |
每周安装量
196
代码仓库
GitHub 星标
3.6K
首次出现
2026年1月22日
安全审计
安装于
opencode190
codex188
gemini-cli187
cursor186
github-copilot183
amp178
Evidence-based patterns for configuring LLM parameters, based on APOLLO and Godel-Prover research.
Different tasks require different LLM configurations. Use these evidence-based settings.
Based on APOLLO parity analysis:
| Parameter | Value | Rationale |
|---|---|---|
| max_tokens | 4096 | Proofs need space for chain-of-thought |
| temperature | 0.6 | Higher creativity for tactic exploration |
| top_p | 0.95 | Allow diverse proof paths |
Always request a proof plan before tactics:
Given the theorem to prove:
[theorem statement]
First, write a high-level proof plan explaining your approach.
Then, suggest Lean 4 tactics to implement each step.
The proof plan (chain-of-thought) significantly improves tactic quality.
For hard proofs, use parallel sampling:
| Parameter | Value | Rationale |
|---|---|---|
| max_tokens | 2048 | Sufficient for most functions |
| temperature | 0.2-0.4 | Prefer deterministic output |
| Parameter | Value | Rationale |
|---|---|---|
| max_tokens | 4096 | Space for exploration |
| temperature | 0.8-1.0 | Maximum creativity |
Weekly Installs
196
Repository
GitHub Stars
3.6K
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode190
codex188
gemini-cli187
cursor186
github-copilot183
amp178
超能力技能使用指南:AI助手技能调用优先级与工作流程详解
46,500 周安装