• Your Name's avatar
    Fix known template fallback and use_manual condition for GGUF models · fb8ec881
    Your Name authored
    - Directly set chat_template to known template names (qwen3, qwen, llama3, etc.)
      instead of trying to load non-existent HuggingFace tokenizers
    - Add use_manual condition to use manual formatting when chat_template is set
      but hf_tokenizer is None (applies to both generate_chat and generate_chat_stream)
    - This ensures GGUF models loaded from URLs with known templates use proper
      <|im_start|> formatting instead of failing on create_chat_completion
    fb8ec881
Name
Last commit
Last update
.vscode Loading commit data...
.gitignore Loading commit data...
LICENSE.md Loading commit data...
README.md Loading commit data...
aaa Loading commit data...
build.sh Loading commit data...
coder Loading commit data...
coderai Loading commit data...
requirements-nvidia.txt Loading commit data...
requirements-vulkan.txt Loading commit data...
requirements.txt Loading commit data...
requirements.txt~ Loading commit data...