44 lines
1.0 KiB
JSON
44 lines
1.0 KiB
JSON
|
|
{
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 131072,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"eos_token_id": 131081,
|
||
|
|
"head_dim": 128,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 16384,
|
||
|
|
"max_position_embeddings": 262144,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 40,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pad_token_id": 131076,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_parameters": {
|
||
|
|
"beta_fast": 32.0,
|
||
|
|
"beta_slow": 1.0,
|
||
|
|
"factor": 16.0,
|
||
|
|
"llama_4_scaling_beta": 0.1,
|
||
|
|
"mscale": 1.0,
|
||
|
|
"mscale_all_dim": 1.0,
|
||
|
|
"original_max_position_embeddings": 16384,
|
||
|
|
"rope_theta": 1000000000.0,
|
||
|
|
"rope_type": "yarn",
|
||
|
|
"type": "yarn"
|
||
|
|
},
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 1000000000.0,
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"transformers_version": "4.57.6",
|
||
|
|
"use_cache": false,
|
||
|
|
"vocab_size": 131328
|
||
|
|
}
|