LLaMA 7B

config.json
{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_sequence_length": 2048,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.28.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}
generation_config.json
1
2
3
4
5
6
7
{
  "_from_model_config": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0,
  "transformers_version": "4.28.0.dev0"
}
tokenizer_config.json
{
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": null,
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}
special_tokens_map.json
{
  "bos_token": {
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "unk_token": {
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}

LLaMA 13B

config.json
{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 13824,
  "max_sequence_length": 2048,
  "model_type": "llama",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.28.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}
generation_config.json
1
2
3
4
5
6
7
{
  "_from_model_config": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0,
  "transformers_version": "4.28.0.dev0"
}
tokenizer_config.json
{
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": null,
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}
special_tokens_map.json
{
  "bos_token": {
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "unk_token": {
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}

LLaMA 33B

config.json
{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 6656,
  "initializer_range": 0.02,
  "intermediate_size": 17920,
  "max_sequence_length": 2048,
  "model_type": "llama",
  "num_attention_heads": 52,
  "num_hidden_layers": 60,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.28.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}
generation_config.json
1
2
3
4
5
6
7
{
  "_from_model_config": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0,
  "transformers_version": "4.28.0.dev0"
}
tokenizer_config.json
{
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": null,
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}
special_tokens_map.json
{
  "bos_token": {
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "unk_token": {
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}

LLaMA 65B

config.json
{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 22016,
  "max_sequence_length": 2048,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-05,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.28.0.dev0",
  "use_cache": true,
  "vocab_size": 32000
}
generation_config.json
1
2
3
4
5
6
7
{
  "_from_model_config": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0,
  "transformers_version": "4.28.0.dev0"
}
tokenizer_config.json
{
  "add_bos_token": true,
  "add_eos_token": false,
  "bos_token": {
    "__type": "AddedToken",
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": false,
  "eos_token": {
    "__type": "AddedToken",
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": null,
  "sp_model_kwargs": {},
  "tokenizer_class": "LlamaTokenizer",
  "unk_token": {
    "__type": "AddedToken",
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}
special_tokens_map.json
{
  "bos_token": {
    "content": "<s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "</s>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "unk_token": {
    "content": "<unk>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  }
}
Edit
Pub: 18 Mar 2023 09:08 UTC
Edit: 07 Apr 2023 15:05 UTC
Views: 11569