From 4601a39c9d4a757fbdfa690e2b7acf8d33ea0408 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sun, 19 Nov 2023 13:34:21 -0300
Subject: [PATCH] Updated Home (markdown)

---
 Home.md | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/Home.md b/Home.md
index 1ea463b..dba34a8 100644
--- a/Home.md
+++ b/Home.md
@@ -2,13 +2,13 @@
 
 | Loader         | Loading 1 LoRA | Loading 2 or more LoRAs | Training LoRAs | Multimodal extension | Perplexity evaluation |
 |----------------|----------------|-------------------------|----------------|----------------------|-----------------------|
-| Transformers   |       ✅       |           ✅            |       ✅*       |          ✅          |           ✅          |
+| Transformers   |       ✅       |           ✅***            |       ✅*       |          ✅          |           ✅          |
 | ExLlama_HF     |       ✅       |           ❌            |       ❌       |          ❌          |           ✅          |
 | ExLlamav2_HF   |       ✅       |           ✅            |       ❌       |          ❌          |           ✅          |
 | ExLlama        |       ✅       |           ❌            |       ❌       |          ❌          |           use ExLlama_HF      |
 | ExLlamav2      |       ✅       |           ✅            |       ❌       |          ❌          |           use ExLlamav2_HF    |
 | AutoGPTQ       |       ✅       |           ❌            |       ❌       |          ✅          |           ✅          |
-| GPTQ-for-LLaMa |       ✅**       |           ✅            |       ✅       |          ✅          |           ✅          |
+| GPTQ-for-LLaMa |       ✅**       |           ✅***            |       ✅       |          ✅          |           ✅          |
 | llama.cpp      |       ❌       |           ❌            |       ❌       |          ❌          |           use llamacpp_HF    |
 | llamacpp_HF    |       ❌       |           ❌            |       ❌       |          ❌          |           ✅          |
 | ctransformers  |       ❌       |           ❌            |       ❌       |          ❌          |           ❌          |
@@ -20,4 +20,6 @@
 
 \* 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).
\ No newline at end of file
+\*\* 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).
+
+\*\*\* Multi-LoRA in PEFT is tricky and the current implementation does not work reliably in all cases.