StackFlow/projects/llm_framework/main_llm/models/mode_llama3.2-1B-p256-ax630c.json

{
    "mode":"llama3.2-1B-p256-ax630c",
    "type":"llm",
    "homepage":"https://huggingface.co/meta-llama/Llama-3.2-1B",
    "capabilities":[
        "text_generation",
        "chat"
    ],
    "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":"llama_post.axmodel",
        "template_filename_axmodel":"llama_p256_l%d_together.axmodel",
        "b_use_topk":false,
        "b_bos":false,
        "b_eos":false,
        "axmodel_num":16,
        "tokens_embed_num":128256,
        "tokens_embed_size":2048,
        "b_use_mmap_load_embed":true,
        "b_dynamic_load_axmodel_layer":false,
        "ext_scripts":["tokenizer_llama3.2-1B-p256-ax630c.py"]
    }
}