43 lines
1.1 KiB
JSON
43 lines
1.1 KiB
JSON
{
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"model_type": "llama",
|
|
"vocab_size": 32000,
|
|
"max_position_embeddings": 512,
|
|
"hidden_size": 768,
|
|
"intermediate_size": 2048,
|
|
"num_hidden_layers": 11,
|
|
"num_attention_heads": 12,
|
|
"head_dim": 64,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": true,
|
|
"hidden_act": "silu",
|
|
"initializer_range": 0.02,
|
|
"bos_token_id": 2,
|
|
"eos_token_id": 3,
|
|
"pad_token_id": 0,
|
|
"torch_dtype": "bfloat16",
|
|
"learnllm": {
|
|
"vocab_size": 32000,
|
|
"context_length": 512,
|
|
"d_model": 768,
|
|
"n_layers": 11,
|
|
"n_heads": 12,
|
|
"head_dim": null,
|
|
"ffn_dim": 2048,
|
|
"dropout": 0.0,
|
|
"bias": false,
|
|
"tie_embeddings": true,
|
|
"norm_type": "rmsnorm",
|
|
"norm_eps": 1e-05,
|
|
"activation": "swiglu",
|
|
"position_encoding": "rope",
|
|
"rope_theta": 10000.0,
|
|
"rope_scaling": null,
|
|
"initializer_range": 0.02,
|
|
"model_type": "llama",
|
|
"architecture_note": "Learned from scratch; parameter names follow the Llama convention so transformers/PEFT/GGUF tools can consume it."
|
|
}
|
|
} |