34 lines
782 B
JSON
34 lines
782 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 0,
|
||
|
|
"eos_token_id": 0,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 960,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 2560,
|
||
|
|
"is_llama_config": true,
|
||
|
|
"max_position_embeddings": 8192,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 15,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 5,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_interleaved": false,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 100000,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.53.2",
|
||
|
|
"unsloth_version": "2025.7.4",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 49152
|
||
|
|
}
|