Merge 28e6bd4fcd into e8595730b4

This reverts commit cc9b7253c1.

README.md

@@ -13,7 +13,7 @@ Its goal is to become the [AUTOMATIC1111/stable-diffusion-webui](https://github.
 ## Features
 
 - Supports multiple text generation backends in one UI/API, including [llama.cpp](https://github.com/ggerganov/llama.cpp), [Transformers](https://github.com/huggingface/transformers), [ExLlamaV3](https://github.com/turboderp-org/exllamav3), [ExLlamaV2](https://github.com/turboderp-org/exllamav2), and [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) (the latter via its own [Dockerfile](https://github.com/oobabooga/text-generation-webui/blob/main/docker/TensorRT-LLM/Dockerfile)).
-- Easy setup: Choose between **portable builds** (zero setup, just unzip and run) for GGUF models on Windows/Linux/macOS, or the one-click installer that creates a self-contained `installer_files` directory without affecting your system.
+- Easy setup: Choose between **portable builds** (zero setup, just unzip and run) for GGUF models on Windows/Linux/macOS, or the one-click installer that creates a self-contained `installer_files` directory.
 - **File attachments**: Upload text files and PDF documents directly in conversations to talk about their contents.
 - **Web search**: Optionally search the internet with LLM-generated queries based on your input to add context to the conversation.
 - Advanced chat management: Edit messages, navigate between message versions, and branch conversations at any point.
@@ -189,13 +189,13 @@ usage: server.py [-h] [--multi-user] [--character CHARACTER] [--model MODEL] [--
                  [--extensions EXTENSIONS [EXTENSIONS ...]] [--verbose] [--idle-timeout IDLE_TIMEOUT] [--loader LOADER] [--cpu] [--cpu-memory CPU_MEMORY] [--disk] [--disk-cache-dir DISK_CACHE_DIR]
                  [--load-in-8bit] [--bf16] [--no-cache] [--trust-remote-code] [--force-safetensors] [--no_use_fast] [--use_flash_attention_2] [--use_eager_attention] [--torch-compile] [--load-in-4bit]
                  [--use_double_quant] [--compute_dtype COMPUTE_DTYPE] [--quant_type QUANT_TYPE] [--flash-attn] [--threads THREADS] [--threads-batch THREADS_BATCH] [--batch-size BATCH_SIZE] [--no-mmap]
-                 [--mlock] [--n-gpu-layers N_GPU_LAYERS] [--tensor-split TENSOR_SPLIT] [--numa] [--no-kv-offload] [--row-split] [--extra-flags EXTRA_FLAGS] [--streaming-llm] [--ctx-size N]
+                 [--mlock] [--gpu-layers N] [--tensor-split TENSOR_SPLIT] [--numa] [--no-kv-offload] [--row-split] [--extra-flags EXTRA_FLAGS] [--streaming-llm] [--ctx-size N] [--cache-type N]
                  [--model-draft MODEL_DRAFT] [--draft-max DRAFT_MAX] [--gpu-layers-draft GPU_LAYERS_DRAFT] [--device-draft DEVICE_DRAFT] [--ctx-size-draft CTX_SIZE_DRAFT] [--gpu-split GPU_SPLIT]
-                 [--autosplit] [--cfg-cache] [--no_flash_attn] [--no_xformers] [--no_sdpa] [--num_experts_per_token N] [--enable_tp] [--hqq-backend HQQ_BACKEND] [--cpp-runner]
-                 [--cache_type CACHE_TYPE] [--deepspeed] [--nvme-offload-dir NVME_OFFLOAD_DIR] [--local_rank LOCAL_RANK] [--alpha_value ALPHA_VALUE] [--rope_freq_base ROPE_FREQ_BASE]
-                 [--compress_pos_emb COMPRESS_POS_EMB] [--listen] [--listen-port LISTEN_PORT] [--listen-host LISTEN_HOST] [--share] [--auto-launch] [--gradio-auth GRADIO_AUTH]
-                 [--gradio-auth-path GRADIO_AUTH_PATH] [--ssl-keyfile SSL_KEYFILE] [--ssl-certfile SSL_CERTFILE] [--subpath SUBPATH] [--old-colors] [--api] [--public-api]
-                 [--public-api-id PUBLIC_API_ID] [--api-port API_PORT] [--api-key API_KEY] [--admin-key ADMIN_KEY] [--api-enable-ipv6] [--api-disable-ipv4] [--nowebui]
+                 [--autosplit] [--cfg-cache] [--no_flash_attn] [--no_xformers] [--no_sdpa] [--num_experts_per_token N] [--enable_tp] [--cpp-runner] [--deepspeed] [--nvme-offload-dir NVME_OFFLOAD_DIR]
+                 [--local_rank LOCAL_RANK] [--alpha_value ALPHA_VALUE] [--rope_freq_base ROPE_FREQ_BASE] [--compress_pos_emb COMPRESS_POS_EMB] [--listen] [--listen-port LISTEN_PORT]
+                 [--listen-host LISTEN_HOST] [--share] [--auto-launch] [--gradio-auth GRADIO_AUTH] [--gradio-auth-path GRADIO_AUTH_PATH] [--ssl-keyfile SSL_KEYFILE] [--ssl-certfile SSL_CERTFILE]
+                 [--subpath SUBPATH] [--old-colors] [--portable] [--api] [--public-api] [--public-api-id PUBLIC_API_ID] [--api-port API_PORT] [--api-key API_KEY] [--admin-key ADMIN_KEY]
+                 [--api-enable-ipv6] [--api-disable-ipv4] [--nowebui]
 
 Text generation web UI
 
@@ -217,7 +217,7 @@ Basic settings:
   --idle-timeout IDLE_TIMEOUT               Unload model after this many minutes of inactivity. It will be automatically reloaded when you try to use it again.
 
 Model loader:
-  --loader LOADER                           Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, ExLlamav3_HF, ExLlamav2_HF, ExLlamav2, HQQ,
+  --loader LOADER                           Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, ExLlamav3_HF, ExLlamav2_HF, ExLlamav2,
                                             TensorRT-LLM.
 
 Transformers/Accelerate:
@@ -248,16 +248,18 @@ llama.cpp:
   --batch-size BATCH_SIZE                   Maximum number of prompt tokens to batch together when calling llama_eval.
   --no-mmap                                 Prevent mmap from being used.
   --mlock                                   Force the system to keep the model in RAM.
-  --n-gpu-layers N_GPU_LAYERS               Number of layers to offload to the GPU.
+  --gpu-layers N, --n-gpu-layers N          Number of layers to offload to the GPU.
   --tensor-split TENSOR_SPLIT               Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.
   --numa                                    Activate NUMA task allocation for llama.cpp.
   --no-kv-offload                           Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.
   --row-split                               Split the model by rows across GPUs. This may improve multi-gpu performance.
-  --extra-flags EXTRA_FLAGS                 Extra flags to pass to llama-server. Format: "flag1=value1;flag2;flag3=value3". Example: "override-tensor=exps=CPU"
+  --extra-flags EXTRA_FLAGS                 Extra flags to pass to llama-server. Format: "flag1=value1,flag2,flag3=value3". Example: "override-tensor=exps=CPU"
   --streaming-llm                           Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.
 
-Context and cache management:
+Context and cache:
   --ctx-size N, --n_ctx N, --max_seq_len N  Context size in tokens.
+  --cache-type N, --cache_type N            KV cache type; valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4; ExLlamaV3 - fp16, q2 to q8 (can specify k_bits and v_bits
+                                            separately, e.g. q4_q8).
 
 Speculative decoding:
   --model-draft MODEL_DRAFT                 Path to the draft model for speculative decoding.
@@ -276,15 +278,9 @@ ExLlamaV2:
   --num_experts_per_token N                 Number of experts to use for generation. Applies to MoE models like Mixtral.
   --enable_tp                               Enable Tensor Parallelism (TP) in ExLlamaV2.
 
-HQQ:
-  --hqq-backend HQQ_BACKEND                 Backend for the HQQ loader. Valid options: PYTORCH, PYTORCH_COMPILE, ATEN.
-
 TensorRT-LLM:
   --cpp-runner                              Use the ModelRunnerCpp runner, which is faster than the default ModelRunner but doesn't support streaming yet.
 
-Cache:
-  --cache_type CACHE_TYPE                   KV cache type; valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4.
-
 DeepSpeed:
   --deepspeed                               Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.
   --nvme-offload-dir NVME_OFFLOAD_DIR       DeepSpeed: Directory to use for ZeRO-3 NVME offloading.
@@ -307,6 +303,7 @@ Gradio:
   --ssl-certfile SSL_CERTFILE               The path to the SSL certificate cert file.
   --subpath SUBPATH                         Customize the subpath for gradio, use with reverse proxy
   --old-colors                              Use the legacy Gradio colors, before the December/2024 update.
+  --portable                                Hide features not available in portable mode like training.
 
 API:
   --api                                     Enable the API extension.

css/main.css

@@ -1,11 +1,11 @@
 :root {
     --darker-gray: #202123;
-    --dark-gray: #343541;
-    --light-gray: #444654;
+    --dark-gray: #2A2B32;
+    --light-gray: #373943;
     --light-theme-gray: #f9fbff;
     --border-color-dark: #525252;
     --header-width: 112px;
-    --selected-item-color-dark: #32333e;
+    --selected-item-color-dark: #2E2F38;
 }
 
 @font-face {
@@ -265,7 +265,7 @@ button {
 
 .dark .pretty_scrollbar::-webkit-scrollbar-thumb,
 .dark .pretty_scrollbar::-webkit-scrollbar-thumb:hover {
-    background: rgb(255 255 255 / 20%);
+    background: rgb(255 255 255 / 10%);
     border-radius: 10px;
 }
 
@@ -1462,6 +1462,7 @@ strong {
 .editing-textarea {
     width: 100%;
     min-height: 200px;
+    max-height: 65vh;
     padding: 10px;
     border-radius: 5px;
     border: 1px solid #ccc;

js/main.js

@@ -171,7 +171,6 @@ const observer = new MutationObserver(function(mutations) {
     document.getElementById("Generate").style.display = "flex";
   }
 
-
   doSyntaxHighlighting();
 
   if (!isScrolled && targetElement.scrollTop !== targetElement.scrollHeight) {
@@ -184,7 +183,10 @@ const observer = new MutationObserver(function(mutations) {
     const lastChild = messagesContainer?.lastElementChild;
     const prevSibling = lastChild?.previousElementSibling;
     if (lastChild && prevSibling) {
-      lastChild.style.minHeight = `calc(max(70vh, 100vh - ${prevSibling.offsetHeight}px - 102px))`;
+      lastChild.style.setProperty("margin-bottom",
+        `max(0px, calc(max(70vh, 100vh - ${prevSibling.offsetHeight}px - 102px) - ${lastChild.offsetHeight}px))`,
+        "important"
+      );
     }
   }
 });

modules/chat.py

@@ -617,10 +617,19 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess
         if regenerate:
             row_idx = len(output['internal']) - 1
 
-            # Store the first response as a version before regenerating
+            # Store the old response as a version before regenerating
             if not output['metadata'].get(f"assistant_{row_idx}", {}).get('versions'):
                 add_message_version(output, "assistant", row_idx, is_current=False)
 
+            # Add new empty version (will be filled during streaming)
+            key = f"assistant_{row_idx}"
+            output['metadata'][key]["versions"].append({
+                "content": "",
+                "visible_content": "",
+                "timestamp": get_current_timestamp()
+            })
+            output['metadata'][key]["current_version_index"] = len(output['metadata'][key]["versions"]) - 1
+
             if loading_message:
                 yield {
                     'visible': output['visible'][:-1] + [[visible_text, shared.processing_message]],
@@ -673,20 +682,34 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess
         if _continue:
             output['internal'][-1] = [text, last_reply[0] + reply]
             output['visible'][-1] = [visible_text, last_reply[1] + visible_reply]
-            if is_stream:
-                yield output
         elif not (j == 0 and visible_reply.strip() == ''):
             output['internal'][-1] = [text, reply.lstrip(' ')]
             output['visible'][-1] = [visible_text, visible_reply.lstrip(' ')]
-            if is_stream:
-                yield output
+
+        # Keep version metadata in sync during streaming (for regeneration)
+        if regenerate:
+            row_idx = len(output['internal']) - 1
+            key = f"assistant_{row_idx}"
+            current_idx = output['metadata'][key]['current_version_index']
+            output['metadata'][key]['versions'][current_idx].update({
+                'content': output['internal'][row_idx][1],
+                'visible_content': output['visible'][row_idx][1]
+            })
+
+        if is_stream:
+            yield output
 
     output['visible'][-1][1] = apply_extensions('output', output['visible'][-1][1], state, is_chat=True)
 
-    # Add the newly generated response as a version (only for regeneration)
+    # Final sync for version metadata (in case streaming was disabled)
     if regenerate:
         row_idx = len(output['internal']) - 1
-        add_message_version(output, "assistant", row_idx, is_current=True)
+        key = f"assistant_{row_idx}"
+        current_idx = output['metadata'][key]['current_version_index']
+        output['metadata'][key]['versions'][current_idx].update({
+            'content': output['internal'][row_idx][1],
+            'visible_content': output['visible'][row_idx][1]
+        })
 
     yield output
 
@@ -1470,7 +1493,7 @@ def handle_edit_message_click(state):
 
     if message_index >= len(history['internal']):
         html_output = redraw_html(history, state['name1'], state['name2'], state['mode'], state['chat_style'], state['character_menu'])
-        return [history, html_output, gr.update()]  # No unique_id change
+        return [history, html_output]
 
     role_idx = 0 if role == "user" else 1
 
@@ -1485,11 +1508,12 @@ def handle_edit_message_click(state):
     if "versions" not in history['metadata'][key] or not history['metadata'][key]["versions"]:
         original_content = history['internal'][message_index][role_idx]
         original_visible = history['visible'][message_index][role_idx]
+        original_timestamp = history['metadata'][key].get('timestamp', get_current_timestamp())
 
         history['metadata'][key]["versions"] = [{
             "content": original_content,
             "visible_content": original_visible,
-            "timestamp": get_current_timestamp()
+            "timestamp": original_timestamp
         }]
 
     history['internal'][message_index][role_idx] = apply_extensions('input', new_text, state, is_chat=True)
@@ -1497,13 +1521,10 @@ def handle_edit_message_click(state):
 
     add_message_version(history, role, message_index, is_current=True)
 
-    # Since we are not branching, unique_id does not change.
-    past_chats_update = gr.update()
-
     save_history(history, state['unique_id'], state['character_menu'], state['mode'])
     html_output = redraw_html(history, state['name1'], state['name2'], state['mode'], state['chat_style'], state['character_menu'])
 
-    return [history, html_output, past_chats_update]
+    return [history, html_output]
 
 
 def handle_navigate_version_click(state):
@@ -1541,6 +1562,7 @@ def handle_navigate_version_click(state):
     history['internal'][message_index][msg_content_idx] = version_to_load['content']
     history['visible'][message_index][msg_content_idx] = version_to_load['visible_content']
     metadata['current_version_index'] = new_idx
+    update_message_metadata(history['metadata'], role, message_index, timestamp=version_to_load['timestamp'])
 
     # Redraw and save
     html = redraw_html(history, state['name1'], state['name2'], state['mode'], state['chat_style'], state['character_menu'])

modules/text_generation.py

@@ -505,11 +505,11 @@ def generate_reply_custom(question, original_question, state, stopping_strings=N
         return
 
 
-def print_prompt(prompt, max_chars=2000):
+def print_prompt(prompt, max_chars=-1):
     DARK_YELLOW = "\033[38;5;3m"
     RESET = "\033[0m"
 
-    if len(prompt) > max_chars:
+    if max_chars > 0 and len(prompt) > max_chars:
         half_chars = max_chars // 2
         hidden_len = len(prompt[half_chars:-half_chars])
         hidden_msg = f"{DARK_YELLOW}[...{hidden_len} characters hidden...]{RESET}"

modules/ui_chat.py

@@ -314,7 +314,7 @@ def create_event_handlers():
 
     shared.gradio['edit_message'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
-        chat.handle_edit_message_click, gradio('interface_state'), gradio('history', 'display', 'unique_id'), show_progress=False)
+        chat.handle_edit_message_click, gradio('interface_state'), gradio('history', 'display'), show_progress=False)
 
     # Save/delete a character
     shared.gradio['save_character'].click(chat.handle_save_character_click, gradio('name2'), gradio('save_character_filename', 'character_saver'), show_progress=False)

modules/utils.py

@@ -74,7 +74,7 @@ def natural_keys(text):
 
 def check_model_loaded():
     if shared.model_name == 'None' or shared.model is None:
-        if len(get_available_models()) <= 1:
+        if len(get_available_models()) == 0:
             error_msg = "No model is loaded.\n\nTo get started:\n1) Place a GGUF file in your user_data/models folder\n2) Go to the Model tab and select it"
             logger.error(error_msg)
             return False, error_msg

requirements/full/requirements.txt

@@ -23,7 +23,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 
@@ -33,8 +33,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cu124-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/v0.14.0/llama_cpp_binaries-0.14.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/exllamav3/releases/download/v0.0.1a9/exllamav3-0.0.1a9+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/oobabooga/exllamav3/releases/download/v0.0.1a9/exllamav3-0.0.1a9+cu124.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/v0.2.9/exllamav2-0.2.9+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

requirements/full/requirements_amd.txt

@@ -22,7 +22,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 
@@ -32,7 +32,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.2.9/exllamav2-0.2.9+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/v0.2.9/exllamav2-0.2.9-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

requirements/full/requirements_amd_noavx2.txt

@@ -22,7 +22,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 
@@ -32,7 +32,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # AMD wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
 https://github.com/turboderp-org/exllamav2/releases/download/v0.2.9/exllamav2-0.2.9+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/v0.2.9/exllamav2-0.2.9-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

requirements/full/requirements_apple_intel.txt

@@ -22,7 +22,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 
@@ -32,7 +32,7 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0-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"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0-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"
 https://github.com/oobabooga/exllamav3/releases/download/v0.0.1a9/exllamav3-0.0.1a9-py3-none-any.whl
 https://github.com/turboderp-org/exllamav2/releases/download/v0.2.9/exllamav2-0.2.9-py3-none-any.whl

requirements/full/requirements_apple_silicon.txt

@@ -22,7 +22,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 
@@ -32,8 +32,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0-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/v0.15.0/llama_cpp_binaries-0.15.0-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/v0.14.0/llama_cpp_binaries-0.14.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0-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/v0.14.0/llama_cpp_binaries-0.14.0-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/exllamav3/releases/download/v0.0.1a9/exllamav3-0.0.1a9-py3-none-any.whl
 https://github.com/turboderp-org/exllamav2/releases/download/v0.2.9/exllamav2-0.2.9-py3-none-any.whl

requirements/full/requirements_cpu_only.txt

@@ -22,7 +22,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 
@@ -32,5 +32,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+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/v0.15.0/llama_cpp_binaries-0.15.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+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/v0.14.0/llama_cpp_binaries-0.14.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

requirements/full/requirements_cpu_only_noavx2.txt

@@ -22,7 +22,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 
@@ -32,5 +32,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+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/v0.15.0/llama_cpp_binaries-0.15.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+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/v0.14.0/llama_cpp_binaries-0.14.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

requirements/full/requirements_noavx2.txt

@@ -23,7 +23,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 
@@ -33,8 +33,8 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cu124avx-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/v0.14.0/llama_cpp_binaries-0.14.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/exllamav3/releases/download/v0.0.1a9/exllamav3-0.0.1a9+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
 https://github.com/oobabooga/exllamav3/releases/download/v0.0.1a9/exllamav3-0.0.1a9+cu124.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/v0.2.9/exllamav2-0.2.9+cu124.torch2.6.0-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"

requirements/full/requirements_nowheels.txt

@@ -22,7 +22,7 @@ safetensors==0.5.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.52.*
+transformers==4.50.*
 tqdm
 wandb
 

requirements/portable/requirements.txt

@@ -18,5 +18,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cu124-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cu124-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

requirements/portable/requirements_apple_intel.txt

@@ -18,5 +18,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0-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/v0.14.0/llama_cpp_binaries-0.14.0-py3-none-macosx_15_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0-py3-none-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0"

requirements/portable/requirements_apple_silicon.txt

@@ -18,6 +18,6 @@ sse-starlette==1.6.5
 tiktoken
 
 # Mac wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0-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/v0.15.0/llama_cpp_binaries-0.15.0-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/v0.14.0/llama_cpp_binaries-0.14.0-py3-none-macosx_15_0_arm64.whl; platform_system == "Darwin" and platform_release >= "24.0.0" and platform_release < "25.0.0"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0-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/v0.14.0/llama_cpp_binaries-0.14.0-py3-none-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0"

requirements/portable/requirements_cpu_only.txt

@@ -18,5 +18,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cpuavx2-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cpuavx2-py3-none-win_amd64.whl; platform_system == "Windows"

requirements/portable/requirements_cpu_only_noavx2.txt

@@ -18,5 +18,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # llama.cpp (CPU only, no AVX2)
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cpuavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cpuavx-py3-none-win_amd64.whl; platform_system == "Windows"

requirements/portable/requirements_noavx2.txt

@@ -18,5 +18,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cu124avx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+cu124avx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

requirements/portable/requirements_vulkan.txt

@@ -18,5 +18,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+vulkan-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+vulkan-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"

requirements/portable/requirements_vulkan_noavx2.txt

@@ -18,5 +18,5 @@ sse-starlette==1.6.5
 tiktoken
 
 # CUDA wheels
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
-https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.15.0/llama_cpp_binaries-0.15.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+vulkanavx-py3-none-win_amd64.whl; platform_system == "Windows"
+https://github.com/oobabooga/llama-cpp-binaries/releases/download/v0.14.0/llama_cpp_binaries-0.14.0+vulkanavx-py3-none-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64"