➡️ Trelis Function-calling Models (incl. Trelis Tiny): https://trelis.com/function-calling/
➡️ ADVANCED-inference Repo: https://trelis.com/enterprise-server-api-and-inference-guide/
➡️ ADVANCED-fine-tuning Repo: https://trelis.com/advanced-fine-tuning-scripts/
➡️ One-click Fine-tuning & Inference Templates: https://github.com/TrelisResearch/one-click-llms/
➡️ Trelis Newsletter: https://Trelis.Substack.com
➡️ Trelis Resources and Support: https://Trelis.com/About
Affiliate Links (support the channel):
- Vast AI - https://cloud.vast.ai/?ref_id=98762
- RunPod - https://tinyurl.com/4b6ecbbn
Resources:
- Slides: http://tinyurl.com/4kvnu4ad
- Chat fine-tuning datasets: https://huggingface.co/collections/Trelis/chat-fine-tuning-datasets-6595dcff8174ea23bccb60df
- One-click LLM templates: https://github.com/TrelisResearch/one-click-llms/tree/main
Models:
- DeepSeek Coder 1.3B: https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct
- Phi 2: https://huggingface.co/microsoft/phi-2
- TinyLlama: https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0
- Trelis Tiny: https://huggingface.co/Trelis/Tiny
Repo Access (purchase includes lifetime access to improvements):
- ADVANCED Fine-tuning: https://trelis.com/advanced-fine-tuning-scripts/
- ADVANCED Inference: https://trelis.com/enterprise-server-api-and-inference-guide/
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.