Menu

#Examples

42 posts

Feed·
20 of 42 posts
Model Evaluation: Benchmarks, Human Evaluation, LLM-as-Judge, and A/B Testing in Production
🖼️
0

Model Evaluation: Benchmarks, Human Evaluation, LLM-as-Judge, and A/B Testing in Production

DEV Community·丁久·21 days ago
#56BjaQm9

Evaluate LLM models systematically using benchmarks, human evaluation, LLM-as-judge frameworks, and production A/B testing.

15s
Read More
AI Role Definition: System Prompts, Personas, Tone Guidelines, Constraints, and Examples
🖼️
0

AI Role Definition: System Prompts, Personas, Tone Guidelines, Constraints, and Examples

DEV Community·丁久·21 days ago
#wE46Q1Gg

Master AI role definition: craft effective system prompts, define personas, set tone guidelines, establish constraints, and provide examples.

15s
Read More
Fine-Tuning Open Source LLMs: A Developer's Practical Guide (2026)
🖼️
0

Fine-Tuning Open Source LLMs: A Developer's Practical Guide (2026)

DEV Community·丁久·22 days ago
#TDKjD4DS

How to fine-tune Llama, Mistral, and other open models: data preparation with JSONL, LoRA vs full fine-tuning, cost comparison, and deployment. Code examples using Together AI and local GPU.

15s
Read More