diff --git a/modules/exllamav2.py b/modules/exllamav2.py
index 2730d9f..551ed49 100644
--- a/modules/exllamav2.py
+++ b/modules/exllamav2.py
@@ -93,17 +93,27 @@ class Exllamav2Model:
 
     def generate_with_streaming(self, prompt, state):
         settings = ExLlamaV2Sampler.Settings()
+
+        settings.token_repetition_penalty = state['repetition_penalty']
+        settings.token_repetition_range = -1 if state['repetition_penalty_range'] <= 0 else state['repetition_penalty_range']
+
+        settings.token_frequency_penalty = state['frequency_penalty']
+        settings.token_presence_penalty = state['presence_penalty']
+
         settings.temperature = state['temperature']
         settings.top_k = state['top_k']
         settings.top_p = state['top_p']
+        settings.top_a = state['top_a']
         settings.min_p = state['min_p']
         settings.tfs = state['tfs']
         settings.typical = state['typical_p']
+
+        settings.temperature_last = state['temperature_last']
+
         settings.mirostat = state['mirostat_mode'] == 2
         settings.mirostat_tau = state['mirostat_tau']
         settings.mirostat_eta = state['mirostat_eta']
-        settings.token_repetition_penalty = state['repetition_penalty']
-        settings.token_repetition_range = -1 if state['repetition_penalty_range'] <= 0 else state['repetition_penalty_range']
+
         if state['ban_eos_token']:
             settings.disallow_tokens(self.tokenizer, [self.tokenizer.eos_token_id])
 
diff --git a/modules/loaders.py b/modules/loaders.py
index 5620c95..2976a85 100644
--- a/modules/loaders.py
+++ b/modules/loaders.py
@@ -205,12 +205,16 @@ loaders_samplers = {
     'HQQ': transformers_samplers(),
     'ExLlamav2': {
         'temperature',
+        'temperature_last',
         'top_p',
         'min_p',
         'top_k',
         'typical_p',
         'tfs',
+        'top_a',
         'repetition_penalty',
+        'presence_penalty',
+        'frequency_penalty',
         'repetition_penalty_range',
         'seed',
         'mirostat_mode',
diff --git a/requirements.txt b/requirements.txt
index 6a60133..54ac7a8 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11; platform_system != "Darwin" and platform_machine != "x86_64"
+exllamav2==0.0.12; platform_system != "Darwin" and platform_machine != "x86_64"
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2
@@ -67,14 +67,14 @@ https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu1
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
diff --git a/requirements_amd.txt b/requirements_amd.txt
index 733d200..6882bc8 100644
--- a/requirements_amd.txt
+++ b/requirements_amd.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11; platform_system == "Windows" or python_version < "3.10" or python_version > "3.11" or platform_machine != "x86_64"
+exllamav2==0.0.12; platform_system == "Windows" or python_version < "3.10" or python_version > "3.11" or platform_machine != "x86_64"
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2
@@ -47,8 +47,8 @@ https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+roc
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
diff --git a/requirements_amd_noavx2.txt b/requirements_amd_noavx2.txt
index 9651171..a8114c6 100644
--- a/requirements_amd_noavx2.txt
+++ b/requirements_amd_noavx2.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11; platform_system == "Windows" or python_version < "3.10" or python_version > "3.11" or platform_machine != "x86_64"
+exllamav2==0.0.12; platform_system == "Windows" or python_version < "3.10" or python_version > "3.11" or platform_machine != "x86_64"
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2
@@ -43,8 +43,8 @@ https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+roc
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
diff --git a/requirements_apple_intel.txt b/requirements_apple_intel.txt
index 2e48ccc..653b8b0 100644
--- a/requirements_apple_intel.txt
+++ b/requirements_apple_intel.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11
+exllamav2==0.0.12
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2
diff --git a/requirements_apple_silicon.txt b/requirements_apple_silicon.txt
index 3e49baa..f3d29f2 100644
--- a/requirements_apple_silicon.txt
+++ b/requirements_apple_silicon.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11
+exllamav2==0.0.12
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2
diff --git a/requirements_cpu_only.txt b/requirements_cpu_only.txt
index 4e89c69..0325a17 100644
--- a/requirements_cpu_only.txt
+++ b/requirements_cpu_only.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11
+exllamav2==0.0.12
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2
diff --git a/requirements_cpu_only_noavx2.txt b/requirements_cpu_only_noavx2.txt
index 0bd630b..6dbb5b6 100644
--- a/requirements_cpu_only_noavx2.txt
+++ b/requirements_cpu_only_noavx2.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11
+exllamav2==0.0.12
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2
diff --git a/requirements_noavx2.txt b/requirements_noavx2.txt
index 5d0cf90..04c948d 100644
--- a/requirements_noavx2.txt
+++ b/requirements_noavx2.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11; platform_system != "Darwin" and platform_machine != "x86_64"
+exllamav2==0.0.12; platform_system != "Darwin" and platform_machine != "x86_64"
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2
@@ -67,14 +67,14 @@ https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu1
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
-https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/jllllll/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu121torch2.1cxx11abiFALSE-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
diff --git a/requirements_nowheels.txt b/requirements_nowheels.txt
index 24a21f3..d67134e 100644
--- a/requirements_nowheels.txt
+++ b/requirements_nowheels.txt
@@ -2,7 +2,7 @@ accelerate==0.25.*
 colorama
 datasets
 einops
-exllamav2==0.0.11
+exllamav2==0.0.12
 gradio==3.50.*
 hqq==0.1.2
 jinja2==3.1.2