Add choice to initial weights with on-the-fly generated weights

[sharlynxy]

• add an argument model_config_path to pass path of model config
• compare model net with the model loaded from pretrained file and they are the same structure

CustomLlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 8192)
    (layers): ModuleList(
      (0-79): 80 x LlamaDecoderLayer(
        (self_attn): LlamaFlashAttention2(
          (qkv_proj): Linear(in_features=8192, out_features=10240, bias=False)
          (o_proj): Linear(in_features=8192, out_features=8192, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=8192, out_features=28672, bias=False)
          (up_proj): Linear(in_features=8192, out_features=28672, bias=False)
          (down_proj): Linear(in_features=28672, out_features=8192, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm()
        (post_attention_layernorm): LlamaRMSNorm()
      )
    )
    (norm): LlamaRMSNorm()
  )
  (lm_head): Linear(in_features=8192, out_features=32000, bias=False)
)

[github-actions]

MLCommons CLA bot:
Thank you very much for your submission, we really appreciate it. Before we can accept your contribution, we ask that you sign the MLCommons CLA (Apache 2). Please use this [Google form] (https://forms.gle/Ew1KkBVpyeJDuRw67) to initiate authorization. If you are from an MLCommons member organization, we will request that you be added to the CLA. If you are not from a member organization, we will email you a CLA to sign. For any questions, please contact [email protected].
0 out of 1 committers have signed the MLCommons CLA.
❌ @sharlynxy
_{You can retrigger this bot by commenting recheck in this Pull Request}