Adding Llama 1B and 3B model.

[githubsgi]

Based on the HuggingFace models ( https://huggingface.co/meta-llama/Llama-3.2-1B and https://huggingface.co/meta-llama/Llama-3.2-3B ) .

1B:

LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(128256, 2048)
    (layers): ModuleList(
      (0-15): 16 x LlamaDecoderLayer(
        (self_attn): LlamaSdpaAttention(
          (q_proj): Linear(in_features=2048, out_features=2048, bias=False)
          (k_proj): Linear(in_features=2048, out_features=512, bias=False)
          (v_proj): Linear(in_features=2048, out_features=512, bias=False)
          (o_proj): Linear(in_features=2048, out_features=2048, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=2048, out_features=8192, bias=False)
          (up_proj): Linear(in_features=2048, out_features=8192, bias=False)
          (down_proj): Linear(in_features=8192, out_features=2048, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((2048,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((2048,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((2048,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=2048, out_features=128256, bias=False)
)

LlamaConfig {
  "_attn_implementation_autoset": true,
  "_name_or_path": "meta-llama/Llama-3.2-1B",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vocab_size": 128256
}

3B:

 LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(128256, 3072)
    (layers): ModuleList(
      (0-27): 28 x LlamaDecoderLayer(
        (self_attn): LlamaSdpaAttention(
          (q_proj): Linear(in_features=3072, out_features=3072, bias=False)
          (k_proj): Linear(in_features=3072, out_features=1024, bias=False)
          (v_proj): Linear(in_features=3072, out_features=1024, bias=False)
          (o_proj): Linear(in_features=3072, out_features=3072, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=3072, out_features=8192, bias=False)
          (up_proj): Linear(in_features=3072, out_features=8192, bias=False)
          (down_proj): Linear(in_features=8192, out_features=3072, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((3072,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((3072,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((3072,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=3072, out_features=128256, bias=False)
)

LlamaConfig {
  "_attn_implementation_autoset": true,
  "_name_or_path": "meta-llama/Llama-3.2-3B",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 24,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.47.1",
  "use_cache": true,
  "vocab_size": 128256
}

[githubsgi]

@tianyu-l , the source is HuggingFace as mentioned above. I am seeing TorchTitan output as follows.

1B: INFO - Model llama3 1B size: 1,397,819,392 total parameters 3B: INFO - Model llama3 3B size: 4,399,475,712 total parameters