magicoder
LLaMA-Factory
| magicoder | LLaMA-Factory | |
|---|---|---|
| 5 | 3 | |
| 1,916 | 23,973 | |
| 1.9% | - | |
| 8.7 | 9.9 | |
| about 1 month ago | 2 days ago | |
| Python | Python | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
magicoder
-
Mistral Magicoder? Any Mistral-based coding models?
Looking at the Magicoder repo, I see that they fine-tuned LLaMA and DeepSeek. (https://github.com/ise-uiuc/magicoder) I'm curious as to why they didn't also use Mistral? Am I missing something obvious?
- Codegen model Magicoder 7B surpasses ChatGPT on HumanEval+ test
- Magicoder: Source Code Is All You Need
- Magicoder, coding-tuned Deepseek-6.7B and Llama-7B. Synth data techniques make it "surpass the ChatGPT on HumanEval+"
LLaMA-Factory
- FLaNK-AIM Weekly 06 May 2024
-
Show HN: GPU Prices on eBay
Depends what model you want to train, and how well you want your computer to keep working while you're doing it.
If you're interested in large language models there's a table of vram requirements for fine-tuning at [1] which says you could do the most basic type of fine-tuning on a 7B parameter model with 8GB VRAM.
You'll find that training takes quite a long time, and as a lot of the GPU power is going on training, your computer's responsiveness will suffer - even basic things like scrolling in your web browser or changing tabs uses the GPU, after all.
Spend a bit more and you'll probably have a better time.
[1] https://github.com/hiyouga/LLaMA-Factory?tab=readme-ov-file#...
- FLaNK Weekly 31 December 2023
What are some alternatives?
monitors4codegen - Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to build applications around language servers.
KVQuant - KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
seatunnel - SeaTunnel is a next-generation super high-performance, distributed, massive data integration tool.
efficient-kan - An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
machinascript-for-robots - Build LLM-powered robots in your garage with MachinaScript For Robots!
HALOs - A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
FLaNK-Ice - Apache Iceberg - Cloud Data Lakehouse
generative-ai-python - The Gemini API Python SDK enables developers to use Google's state-of-the-art generative AI models to build AI-powered features and applications.
autoquizzer - Generates a quiz from a URL. You can play the quiz, or let the LLM play it.
Stirling-PDF - #1 Locally hosted web application that allows you to perform various operations on PDF files
kamal - Deploy web apps anywhere.
promptbench - A unified evaluation framework for large language models