Merge pull request oobabooga#5502 from oobabooga/dev

Merge dev branch

Author: oobabooga

.github/workflows/stale.yml

@@ -13,8 +13,8 @@ jobs:
       - uses: actions/stale@v5
         with:
           stale-issue-message: ""
-          close-issue-message: "This issue has been closed due to inactivity for 6 weeks. If you believe it is still relevant, please leave a comment below. You can tag a developer in your comment."
-          days-before-issue-stale: 42
+          close-issue-message: "This issue has been closed due to inactivity for 2 months. If you believe it is still relevant, please leave a comment below. You can tag a developer in your comment."
+          days-before-issue-stale: 60
           days-before-issue-close: 0
           stale-issue-label: "stale"
           days-before-pr-stale: -1

modules/models.py

@@ -254,26 +254,17 @@ def llamacpp_loader(model_name):
 def llamacpp_HF_loader(model_name):
     from modules.llamacpp_hf import LlamacppHF
 
-    for fname in [model_name, "oobabooga_llama-tokenizer", "llama-tokenizer"]:
-        path = Path(f'{shared.args.model_dir}/{fname}')
-        if all((path / file).exists() for file in ['tokenizer_config.json', 'special_tokens_map.json', 'tokenizer.model']):
-            logger.info(f'Using tokenizer from: \"{path}\"')
-            break
+    path = Path(f'{shared.args.model_dir}/{model_name}')
+
+    # Check if a HF tokenizer is available for the model
+    if all((path / file).exists() for file in ['tokenizer.model', 'tokenizer_config.json']):
+        logger.info(f'Using tokenizer from: \"{path}\"')
     else:
-        logger.error("Could not load the model because a tokenizer in transformers format was not found. Please download oobabooga/llama-tokenizer.")
+        logger.error("Could not load the model because a tokenizer in Transformers format was not found.")
         return None, None
 
-    if shared.args.no_use_fast:
-        logger.info('Loading the tokenizer with use_fast=False.')
-
-    tokenizer = AutoTokenizer.from_pretrained(
-        path,
-        trust_remote_code=shared.args.trust_remote_code,
-        use_fast=not shared.args.no_use_fast
-    )
-
     model = LlamacppHF.from_pretrained(model_name)
-    return model, tokenizer
+    return model
 
 
 def ctransformers_loader(model_name):

modules/ui_model_menu.py

@@ -143,7 +143,7 @@ def create_ui():
                             shared.gradio['disable_exllamav2'] = gr.Checkbox(label="disable_exllamav2", value=shared.args.disable_exllamav2, info='Disable ExLlamav2 kernel for GPTQ models.')
                             shared.gradio['gptq_for_llama_info'] = gr.Markdown('Legacy loader for compatibility with older GPUs. ExLlamav2_HF or AutoGPTQ are preferred for GPTQ models when supported.')
                             shared.gradio['exllamav2_info'] = gr.Markdown("ExLlamav2_HF is recommended over ExLlamav2 for better integration with extensions and more consistent sampling behavior across loaders.")
-                            shared.gradio['llamacpp_HF_info'] = gr.Markdown('llamacpp_HF loads llama.cpp as a Transformers model. To use it, you need to download a tokenizer.\n\nOption 1 (recommended): place your .gguf in a subfolder of models/ along with these 4 files: special_tokens_map.json, tokenizer_config.json, tokenizer.json, tokenizer.model.\n\nOption 2: download `oobabooga/llama-tokenizer` under "Download model or LoRA". That\'s a default Llama tokenizer that will work for some (but not all) models.')
+                            shared.gradio['llamacpp_HF_info'] = gr.Markdown("llamacpp_HF loads llama.cpp as a Transformers model. To use it, download a tokenizer in HF format for your GGUF:\n\n1. Create a folder inside models/\n2. Place your GGUF in the new folder.\n3. Add the original model's tokenizer files there: `tokenizer.model`, `tokenizer_config.json`, `tokenizer.json`, and `special_tokens_map.json`.")
 
             with gr.Column():
                 with gr.Row():

requirements.txt

@@ -50,11 +50,11 @@ 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-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 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/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
+https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
 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/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"

requirements_noavx2.txt

@@ -50,11 +50,11 @@ 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-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 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/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and platform_machine == "x86_64" and python_version == "3.11"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and platform_machine == "x86_64" and python_version == "3.10"
+https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
+https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
 https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
-https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
+https://github.com/oobabooga/exllamav2/releases/download/v0.0.13.1/exllamav2-0.0.13.1-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
 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/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"