|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
extra_gated_prompt: >- |
|
To gain access, [subscribe to The Kaitchup |
|
Pro](https://newsletter.kaitchup.com/subscribe). You will receive an access |
|
token for all the toolboxes in your welcome email. You can also purchase an |
|
access specifically for this repository on |
|
[Gumroad](https://benjaminmarie.gumroad.com/l/llama-3-toolbox). Once you have access, you can request for help and suggest new notebooks through the community tab. |
|
datasets: |
|
- mlabonne/orpo-dpo-mix-40k |
|
- HuggingFaceH4/ultrachat_200k |
|
--- |
|
|
|
This toolbox already includes 19 Jupyter notebooks specially optimized for [Llama 3.1](https://huggingface.co/collections/meta-llama/llama-31-669fc079a0c406a149a5738f) amd [Llama 3.2](https://huggingface.co/collections/meta-llama/llama-32-66f448ffc8c32f949b04c8cf) LLMs. The logs of successful runs are also provided. More notebooks will be regularly added. |
|
|
|
Once you've subscribed to The Kaitchup Pro or purchased access, you can also request repository access here. |
|
|
|
To run the code in the toolbox, CUDA 12.4 and PyTorch 2.4 are recommended. PyTorch 2.5 might already work but I didn't test it yet. |
|
|
|
# Toolbox content |
|
|
|
* Supervised Fine-Tuning with Chat Templates (6 notebooks) |
|
|
|
* Full fine-tuning |
|
|
|
* LoRA fine-tuning |
|
|
|
* LoRA fine-tuning (with Llama 3.1/3.2 Instruct) |
|
|
|
* Multi-GPU QLoRA/LoRA fine-tuning with FSDP (with Llama 3.1/3.2 Instruct) |
|
|
|
* QLoRA fine-tuning with Bitsandbytes quantization |
|
|
|
* QLoRA fine-tuning with AutoRound quantization |
|
|
|
* LoRA and QLoRA fine-tuning with Unsloth |
|
|
|
* Preference Optimization (2 notebooks) |
|
|
|
* DPO training with LoRA (TRL and Transformers) |
|
|
|
* ORPO training with LoRA (TRL and Transformers) |
|
|
|
* Multi-GPU QLoRA/LoRA DPO Training with FSDP |
|
|
|
* Quantization (3 notebooks) |
|
|
|
* AWQ |
|
|
|
* AutoRound |
|
|
|
* GGUF for llama.cpp |
|
|
|
* Inference (4 notebooks) |
|
|
|
* Transformers with and without a LoRA adapter |
|
|
|
* vLLM offline and online inference |
|
|
|
* Ollama |
|
|
|
* llama.cpp |
|
|
|
* Merging (3 notebooks) |
|
|
|
* Merge a LoRA adapter into the base model |
|
|
|
* Merge a QLoRA adapter into the base model |
|
|
|
* Merge several Llama 3.1/3.2 models into one with mergekit (not released yet) |
