diff --git a/.github/workflows/build-portable-release-cuda.yml b/.github/workflows/build-portable-release-cuda.yml
index 2d2685dd..3b1ab8a8 100644
--- a/.github/workflows/build-portable-release-cuda.yml
+++ b/.github/workflows/build-portable-release-cuda.yml
@@ -60,7 +60,7 @@ jobs:
               'os' = @('ubuntu-22.04', 'windows-2022')
               'pyver' = @("3.11")
               'avx' = @("AVX2")
-              'cuda' = @("11.7", "12.4")
+              'cuda' = @("12.4")
           }
 
           if ($env:CONFIGIN -ne 'Default') {$env:CONFIGIN.split(';').foreach({$matrix[$_.split(':')[0]] = $_.split(':')[1].split(',')})}
@@ -147,22 +147,13 @@ jobs:
 
             # Create CUDA-specific requirements file if needed
             cd "text-generation-webui-${VERSION_CLEAN}"
-            if [[ "$CUDA_VERSION" == "11.7" ]]; then
-                echo "Creating CUDA 11.7 specific requirements file"
-                sed 's/cu124/cu117/g' "$BASE_REQ_FILE" > requirements_cuda_temp.txt
-                REQ_FILE="requirements_cuda_temp.txt"
-            else
-                REQ_FILE="$BASE_REQ_FILE"
-            fi
+            REQ_FILE="$BASE_REQ_FILE"
 
             # 4. Install packages
             echo "Installing Python packages from $REQ_FILE..."
             $PIP_PATH install --target="./$PACKAGES_PATH" -r "$REQ_FILE"
 
             # 5. Clean up
-            if [[ "$CUDA_VERSION" == "11.7" ]]; then
-                rm requirements_cuda_temp.txt
-            fi
             rm -rf .git cmd* update_wizard* Colab-TextGen-GPU.ipynb docker setup.cfg .github .gitignore requirements/ one_click.py
 
             # 6. Create ZIP file
diff --git a/extensions/Training_PRO/script.py b/extensions/Training_PRO/script.py
index cb11a8df..e2f90f17 100644
--- a/extensions/Training_PRO/script.py
+++ b/extensions/Training_PRO/script.py
@@ -823,7 +823,7 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
         lora_model = get_peft_model(shared.model, config)
         if not always_override and Path(f"{lora_file_path}/adapter_model.bin").is_file():
             logger.info("Loading existing LoRA data...")
-            state_dict_peft = torch.load(f"{lora_file_path}/adapter_model.bin")
+            state_dict_peft = torch.load(f"{lora_file_path}/adapter_model.bin", weights_only=True)
             set_peft_model_state_dict(lora_model, state_dict_peft)
 
             print(f" + Continue Training on {RED}{lora_file_path}/adapter_model.bin{RESET}")
diff --git a/modules/training.py b/modules/training.py
index 2354c39d..1de0b702 100644
--- a/modules/training.py
+++ b/modules/training.py
@@ -611,7 +611,7 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
             bf16=shared.args.bf16,
             optim=optimizer,
             logging_steps=2 if stop_at_loss > 0 else 5,
-            evaluation_strategy="steps" if eval_data is not None else "no",
+            eval_strategy="steps" if eval_data is not None else "no",
             eval_steps=math.ceil(eval_steps / gradient_accumulation_steps) if eval_data is not None else None,
             save_strategy="steps" if eval_data is not None else "no",
             output_dir=lora_file_path,
@@ -620,7 +620,7 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
             # TODO: Enable multi-device support
             ddp_find_unused_parameters=None,
             no_cuda=shared.args.cpu,
-            use_ipex=True if is_torch_xpu_available() and not shared.args.cpu else False
+            # use_ipex=True if is_torch_xpu_available() and not shared.args.cpu else False
         ),
         data_collator=transformers.DataCollatorForLanguageModeling(shared.tokenizer, mlm=False),
         callbacks=list([Callbacks()])
diff --git a/requirements/full/requirements.txt b/requirements/full/requirements.txt
index 6b579bc4..aa666532 100644
--- a/requirements/full/requirements.txt
+++ b/requirements/full/requirements.txt
@@ -5,8 +5,9 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-flash-linear-attention==0.3.2
+flash-linear-attention==0.4.0
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -39,10 +40,10 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.11/exllamav3-0.0.11+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.11/exllamav3-0.0.11+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp-org/exllamav3/releases/download/v0.0.12/exllamav3-0.0.12+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp-org/exllamav3/releases/download/v0.0.12/exllamav3-0.0.12+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_amd.txt b/requirements/full/requirements_amd.txt
index 277beb86..3bdb0774 100644
--- a/requirements/full/requirements_amd.txt
+++ b/requirements/full/requirements_amd.txt
@@ -5,6 +5,7 @@ datasets
 einops
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -37,7 +38,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_amd_noavx2.txt b/requirements/full/requirements_amd_noavx2.txt
index 4637702e..0ad11242 100644
--- a/requirements/full/requirements_amd_noavx2.txt
+++ b/requirements/full/requirements_amd_noavx2.txt
@@ -5,6 +5,7 @@ datasets
 einops
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -37,7 +38,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+rocm6.2.4.torch2.6.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_apple_intel.txt b/requirements/full/requirements_apple_intel.txt
index 7784181d..6212441e 100644
--- a/requirements/full/requirements_apple_intel.txt
+++ b/requirements/full/requirements_apple_intel.txt
@@ -5,6 +5,7 @@ datasets
 einops
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -37,5 +38,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
\ No newline at end of file
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
diff --git a/requirements/full/requirements_apple_silicon.txt b/requirements/full/requirements_apple_silicon.txt
index 88b4effb..a24cdd7a 100644
--- a/requirements/full/requirements_apple_silicon.txt
+++ b/requirements/full/requirements_apple_silicon.txt
@@ -5,6 +5,7 @@ datasets
 einops
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -37,6 +38,6 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
diff --git a/requirements/full/requirements_cpu_only.txt b/requirements/full/requirements_cpu_only.txt
index aca3e51f..62dc99e0 100644
--- a/requirements/full/requirements_cpu_only.txt
+++ b/requirements/full/requirements_cpu_only.txt
@@ -5,6 +5,7 @@ datasets
 einops
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -37,5 +38,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/full/requirements_cpu_only_noavx2.txt b/requirements/full/requirements_cpu_only_noavx2.txt
index e75df348..7f889de2 100644
--- a/requirements/full/requirements_cpu_only_noavx2.txt
+++ b/requirements/full/requirements_cpu_only_noavx2.txt
@@ -5,6 +5,7 @@ datasets
 einops
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -37,5 +38,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
diff --git a/requirements/full/requirements_noavx2.txt b/requirements/full/requirements_noavx2.txt
index 16dfea5a..74758177 100644
--- a/requirements/full/requirements_noavx2.txt
+++ b/requirements/full/requirements_noavx2.txt
@@ -5,8 +5,9 @@ colorama
 datasets
 einops
 fastapi==0.112.4
-flash-linear-attention==0.3.2
+flash-linear-attention==0.4.0
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -39,10 +40,10 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.11/exllamav3-0.0.11+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/turboderp-org/exllamav3/releases/download/v0.0.11/exllamav3-0.0.11+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
+https://github.com/turboderp-org/exllamav3/releases/download/v0.0.12/exllamav3-0.0.12+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/turboderp-org/exllamav3/releases/download/v0.0.12/exllamav3-0.0.12+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2+cu128.torch2.7.0-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.3.2/exllamav2-0.3.2-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
diff --git a/requirements/full/requirements_nowheels.txt b/requirements/full/requirements_nowheels.txt
index 2bb65a1d..09a12418 100644
--- a/requirements/full/requirements_nowheels.txt
+++ b/requirements/full/requirements_nowheels.txt
@@ -5,6 +5,7 @@ datasets
 einops
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
diff --git a/requirements/portable/requirements.txt b/requirements/portable/requirements.txt
index c5885c3e..f5c10dc4 100644
--- a/requirements/portable/requirements.txt
+++ b/requirements/portable/requirements.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -22,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_apple_intel.txt b/requirements/portable/requirements_apple_intel.txt
index a50a3e84..2dc56261 100644
--- a/requirements/portable/requirements_apple_intel.txt
+++ b/requirements/portable/requirements_apple_intel.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -22,6 +23,6 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
diff --git a/requirements/portable/requirements_apple_silicon.txt b/requirements/portable/requirements_apple_silicon.txt
index df0beb22..0256fe98 100644
--- a/requirements/portable/requirements_apple_silicon.txt
+++ b/requirements/portable/requirements_apple_silicon.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -22,6 +23,6 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"
diff --git a/requirements/portable/requirements_cpu_only.txt b/requirements/portable/requirements_cpu_only.txt
index 75e60b8c..9f68d17c 100644
--- a/requirements/portable/requirements_cpu_only.txt
+++ b/requirements/portable/requirements_cpu_only.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -22,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_cpu_only_noavx2.txt b/requirements/portable/requirements_cpu_only_noavx2.txt
index b9835fa1..7a444f81 100644
--- a/requirements/portable/requirements_cpu_only_noavx2.txt
+++ b/requirements/portable/requirements_cpu_only_noavx2.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -22,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
diff --git a/requirements/portable/requirements_noavx2.txt b/requirements/portable/requirements_noavx2.txt
index 7cf4755d..68cb06b7 100644
--- a/requirements/portable/requirements_noavx2.txt
+++ b/requirements/portable/requirements_noavx2.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -22,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_nowheels.txt b/requirements/portable/requirements_nowheels.txt
index 1a7b5683..c9831985 100644
--- a/requirements/portable/requirements_nowheels.txt
+++ b/requirements/portable/requirements_nowheels.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
diff --git a/requirements/portable/requirements_vulkan.txt b/requirements/portable/requirements_vulkan.txt
index 035c8d4e..350ddb09 100644
--- a/requirements/portable/requirements_vulkan.txt
+++ b/requirements/portable/requirements_vulkan.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -22,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
diff --git a/requirements/portable/requirements_vulkan_noavx2.txt b/requirements/portable/requirements_vulkan_noavx2.txt
index bb3bd518..4a88967d 100644
--- a/requirements/portable/requirements_vulkan_noavx2.txt
+++ b/requirements/portable/requirements_vulkan_noavx2.txt
@@ -1,6 +1,7 @@
 audioop-lts<1.0; python_version >= "3.13"
 fastapi==0.112.4
 html2text==2025.4.15
+huggingface-hub==0.36.0
 jinja2==3.1.6
 markdown
 numpy==2.2.*
@@ -22,5 +23,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.56.0/llama_cpp_binaries-0.56.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.60.0/llama_cpp_binaries-0.60.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"