StackFlow/projects/llm_framework/main_llm/models/mode_qwen2.5-coder-0.5B-ax630c.json

{
    "mode":"qwen2.5-coder-0.5B-ax630c",
    "type":"llm",
    "homepage":"https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct",
    "capabilities":[
        "text_generation",
        "code_generation"
    ],
    "input_type":[
        "llm.utf-8",
        "llm.utf-8.stream",
        "llm.chat_completion",
        "llm.chat_completion.stream"
    ],
    "output_type":[
        "llm.utf-8",
        "llm.utf-8.stream"
    ],
    "mode_param":{
        "tokenizer_type":2,
        "filename_tokenizer_model":"http://localhost:8080",
        "filename_tokens_embed":"model.embed_tokens.weight.bfloat16.bin",
        "filename_post_axmodel":"qwen2_post.axmodel",
        "template_filename_axmodel":"qwen2_p128_l%d_together.axmodel",
        "b_use_topk":false,
        "b_bos":false,
        "b_eos":false,
        "axmodel_num":24,
        "tokens_embed_num":151936,
        "tokens_embed_size":896,
        "b_use_mmap_load_embed":true,
        "b_dynamic_load_axmodel_layer":false,
        "ext_scripts":["tokenizer_qwen2.5-coder-0.5B-ax630c.py"]
    }
}