35 lines
1.1 KiB
JSON
35 lines
1.1 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": true,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 0,
|
||
|
|
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|system|>\n{{ message['content'] }}\n{% elif message['role'] == 'user' %}<|user|>\n{{ message['content'] }}\n{% elif message['role'] == 'assistant' %}<|assistant|>\n{{ message['content'] }}{% if not loop.last %}\n{% endif %}{% endif %}{% endfor %}{% if messages[-1]['role'] != 'assistant' %}<|assistant|>\n{% endif %}",
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"eos_token_id": 0,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_dropout": 0.0,
|
||
|
|
"hidden_size": 576,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 1536,
|
||
|
|
"max_position_embeddings": 2048,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 9,
|
||
|
|
"num_hidden_layers": 30,
|
||
|
|
"num_key_value_heads": 3,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_parameters": {
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"rope_type": "default"
|
||
|
|
},
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"transformers_version": "5.6.0",
|
||
|
|
"use_cache": false,
|
||
|
|
"vocab_size": 49152
|
||
|
|
}
|