➡️ Trelis Function-calling Models (incl. Trelis Tiny): [ Ссылка ]
➡️ ADVANCED-inference Repo: [ Ссылка ]
➡️ ADVANCED-fine-tuning Repo: [ Ссылка ]
➡️ One-click Fine-tuning & Inference Templates: [ Ссылка ]
➡️ Trelis Newsletter: [ Ссылка ]
➡️ Trelis Resources and Support: [ Ссылка ]

Affiliate Links (support the channel):
- Vast AI - [ Ссылка ]
- RunPod - [ Ссылка ]

Resources:
- Slides: [ Ссылка ]
- Chat fine-tuning datasets: [ Ссылка ]
- One-click LLM templates: [ Ссылка ]

Models:
- DeepSeek Coder 1.3B: [ Ссылка ]
- Phi 2: [ Ссылка ]
- TinyLlama: [ Ссылка ]
- Trelis Tiny: [ Ссылка ]

Repo Access (purchase includes lifetime access to improvements):
- ADVANCED Fine-tuning: [ Ссылка ]
- ADVANCED Inference: [ Ссылка ]

Chapters:
0:00 Best Small Language Models
0:19 Video Overview
1:23 Benefits of Tiny LLMs
2:09 Fine-tuning and Inference Repo Overviews
4:28 Performance Comparison - TinyLlama, DeepSeek Coder and Phi 2
16:21 Fine-tuning Tiny Language Models
33:55 Function-calling quantized models with llama.cpp
44:44 Challenges and Tricks - Function-calling with Tiny Models
1:00:00 What are the best Tiny Language models?

Reminder: Be careful when using private keys (e.g. OpenAI or HuggingFace). If they are exposed, make sure to rotate them, as I do after each video.

свернуть