text-generation-webui/docs/What Works.md

26 lines
2.2 KiB
Markdown
Raw Normal View History

2023-10-22 00:15:54 +02:00
## What Works
| Loader | Loading 1 LoRA | Loading 2 or more LoRAs | Training LoRAs | Multimodal extension | Perplexity evaluation |
|----------------|----------------|-------------------------|----------------|----------------------|-----------------------|
2023-11-19 16:57:16 +01:00
| Transformers | ✅ | ✅*** | ✅* | ✅ | ✅ |
2023-10-22 00:15:54 +02:00
| ExLlama_HF | ✅ | ❌ | ❌ | ❌ | ✅ |
| ExLlamav2_HF | ✅ | ✅ | ❌ | ❌ | ✅ |
| ExLlama | ✅ | ❌ | ❌ | ❌ | use ExLlama_HF |
| ExLlamav2 | ✅ | ✅ | ❌ | ❌ | use ExLlamav2_HF |
| AutoGPTQ | ✅ | ❌ | ❌ | ✅ | ✅ |
2023-11-19 16:57:16 +01:00
| GPTQ-for-LLaMa | ✅** | ✅*** | ✅ | ✅ | ✅ |
2023-10-22 00:15:54 +02:00
| llama.cpp | ❌ | ❌ | ❌ | ❌ | use llamacpp_HF |
| llamacpp_HF | ❌ | ❌ | ❌ | ❌ | ✅ |
| ctransformers | ❌ | ❌ | ❌ | ❌ | ❌ |
| AutoAWQ | ? | ❌ | ? | ? | ✅ |
❌ = not implemented
✅ = implemented
\* Training LoRAs with GPTQ models also works with the Transformers loader. Make sure to check "auto-devices" and "disable_exllama" before loading the model.
\*\* Requires the monkey-patch. The instructions can be found [here](https://github.com/oobabooga/text-generation-webui/wiki/08-%E2%80%90-Additional-Tips#using-loras-with-gptq-for-llama).
2023-11-19 16:57:16 +01:00
\*\*\* Multi-LoRA in PEFT is tricky and the current implementation does not work reliably in all cases.