LLM调优模式指南：基于APOLLO研究的参数配置与提示工程最佳实践

llm-tuning-patterns by parcadei/continuous-claude-v3

196 周安装量

3,600 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/parcadei/continuous-claude-v3 --skill llm-tuning-patterns

AI/机器学习代码生成提示工程

🇨🇳中文介绍

LLM 调优模式

基于 APOLLO 和 Godel-Prover 研究的、有实证依据的 LLM 参数配置模式。

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。

定理证明 / 形式推理

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

证明计划提示

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。

并行采样

对于困难的证明，使用并行采样：

生成 N=8-32 个候选证明尝试

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

联系我们

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

🇺🇸English

LLM Tuning Patterns

Evidence-based patterns for configuring LLM parameters, based on APOLLO and Godel-Prover research.

Pattern

Different tasks require different LLM configurations. Use these evidence-based settings.

Theorem Proving / Formal Reasoning

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

Proof Plan Prompt

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.

Parallel Sampling

For hard proofs, use parallel sampling:

Generate N=8-32 candidate proof attempts
Use best-of-N selection
Each sample at temperature 0.6-0.8

Code Generation

Parameter	Value	Rationale
max_tokens	2048	Sufficient for most functions
temperature	0.2-0.4	Prefer deterministic output

Creative / Exploration Tasks

Parameter	Value	Rationale
max_tokens	4096	Space for exploration
temperature	0.8-1.0	Maximum creativity

Anti-Patterns

Too low tokens for proofs : 512 tokens truncates chain-of-thought
Too low temperature for proofs : 0.2 misses creative tactic paths
No proof plan : Jumping to tactics without planning reduces success rate

Source Sessions

This session: APOLLO parity - increased max_tokens 512->4096, temp 0.2->0.6
This session: Added proof plan prompt for chain-of-thought before tactics

Weekly Installs

196

Repository

parcadei/contin…laude-v3

GitHub Stars

3.6K

First Seen

Jan 22, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

opencode190

codex188

gemini-cli187

cursor186

github-copilot183

amp178