maxbbraun / maxbbraun/llama4micro
Try llama.cpp/ggml
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 561
- Forks
- 37
- PR merge metrics
- No merged PRs in 30d
Description
The main reason I chose karpathy/llama2.c over ggerganov/llama.cpp initially was that the former comes out of the box with very small (15M) models.
llama.cpp and ggml more generally is a more mature system with a number of optimizations including 4-bit quantization. Seems worth a try! Might have to train a right-sized model from scratch though.
Potentially relevant examples:
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the linked llama.cpp and ggml projects, especially examples/baby-llama and examples/train-text-from-scratch. The issue does not specify an implementation entry point, target model, or completion criteria, so a concrete scope and definition of done are needed before work can begin.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- embedded-iot, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100