From 2f935547c8ee4b34754bd15d64ca5ecced340205 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Tue, 12 Sep 2023 15:05:21 -0700
Subject: [PATCH] Minor changes

---
 README.md          |  2 +-
 modules/loaders.py | 14 +++++++-------
 modules/shared.py  |  4 ++--
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/README.md b/README.md
index 24fc17bc..da87da10 100644
--- a/README.md
+++ b/README.md
@@ -335,7 +335,7 @@ Optionally, you can use the following command-line flags:
 | `--rwkv-strategy RWKV_STRATEGY` | RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8". |
 | `--rwkv-cuda-on`                | RWKV: Compile the CUDA kernel for better performance. |
 
-#### RoPE (for llama.cpp, ExLlama, and transformers)
+#### RoPE (for llama.cpp, ExLlama, ExLlamaV2, and transformers)
 
 | Flag             | Description |
 |------------------|-------------|
diff --git a/modules/loaders.py b/modules/loaders.py
index 15dd4668..ff2f5050 100644
--- a/modules/loaders.py
+++ b/modules/loaders.py
@@ -34,6 +34,13 @@ loaders_and_params = OrderedDict({
         'cfg_cache',
         'exllama_HF_info',
     ],
+    'ExLlamav2_HF': [
+        'gpu_split',
+        'max_seq_len',
+        'cfg_cache',
+        'alpha_value',
+        'compress_pos_emb',
+    ],
     'ExLlama': [
         'gpu_split',
         'max_seq_len',
@@ -48,13 +55,6 @@ loaders_and_params = OrderedDict({
         'alpha_value',
         'compress_pos_emb',
     ],
-    'ExLlamav2_HF': [
-        'gpu_split',
-        'max_seq_len',
-        'cfg_cache',
-        'alpha_value',
-        'compress_pos_emb',
-    ],
     'AutoGPTQ': [
         'triton',
         'no_inject_fused_attention',
diff --git a/modules/shared.py b/modules/shared.py
index 829d7c01..06aafc8d 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -219,9 +219,9 @@ def fix_loader_name(name):
         return 'ExLlama'
     elif name in ['exllama-hf', 'exllama_hf', 'exllama hf', 'ex-llama-hf', 'ex_llama_hf']:
         return 'ExLlama_HF'
-    elif name in ['exllamav2', 'exllama-v2', 'ex_llama-v2', 'exlamav2', 'exlama-v2']:
+    elif name in ['exllamav2', 'exllama-v2', 'ex_llama-v2', 'exlamav2', 'exlama-v2', 'exllama2', 'exllama-2']:
         return 'ExLlamav2'
-    elif name in ['exllamav2-hf', 'exllamav2_hf', 'exllama-v2-hf', 'exllama_v2_hf', 'exllama-v2_hf']:
+    elif name in ['exllamav2-hf', 'exllamav2_hf', 'exllama-v2-hf', 'exllama_v2_hf', 'exllama-v2_hf', 'exllama2-hf', 'exllama2_hf', 'exllama-2-hf', 'exllama_2_hf', 'exllama-2_hf']:
         return 'ExLlamav2_HF'
     elif name in ['ctransformers', 'ctranforemrs', 'ctransformer']:
         return 'ctransformers'