CODE

–

23 March 2024 22h52

I mostly just use Weights + Biases for tracking.

Build Your Ideas Using LLMs as Your Development Partner

By

–

23 March 2024 22h51

Decide what you want to build and just go for it. Ask LLMs for help when you need it. This is the way.

Using Claude Haiku for cost-effective prompt stuffing

By

–

23 March 2024 22h47

If it’s under 200k tokens and I can afford it, I’m using Claude Haiku and stuffing it all in the prompt.

AI Development Stack: Local Setup with Cloud Compute

By

–

23 March 2024 22h34

My couch. MacBook Pro. Runpod for compute. Axolotl for training. OpenAI Playground and Anthropic Console for prompt engineering. Sometimes PromptKnit.

Complete AI Development Stack: Runpod, Axolotl, and Prompt Engineering

By

–

23 March 2024 22h33

My couch. MacBook Pro. Runpod for compute. Axolotl for training. OpenAI Playground and Anthropic Console for prompt engineering. Sometimes PromptKnit.

Fine-tune Mistral-7B with synthetic prompt-response datasets

By

–

23 March 2024 22h24

Switch all prompts to mistral-large. Run the repo many times, collect the prompts / responses for each input / output. Format as JSONL, train a Mistral-7B or similar on all of them, and slot it in.

API Optimization and qLoRA Fine-tuning Techniques

By

–

23 March 2024 22h21

On APIs, it’s hard but if you’re going after a specific use-case it just takes a bit of tinkering with the prompt. If not, just do a qLoRA with a couple hundred negative examples and you’re all set.