30 lines
720 B
JSON
30 lines
720 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Qwen3ForCausalLM"
|
||
|
|
],
|
||
|
|
"model_type": "qwen3",
|
||
|
|
"vocab_size": 6400,
|
||
|
|
"hidden_size": 768,
|
||
|
|
"intermediate_size": 2432,
|
||
|
|
"num_hidden_layers": 8,
|
||
|
|
"num_attention_heads": 8,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"head_dim": 96,
|
||
|
|
"max_position_embeddings": 2048,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"use_cache": true,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"miniMindScratch": {
|
||
|
|
"param_count": 63912192,
|
||
|
|
"state_tensor_count": 68827392,
|
||
|
|
"source_architecture": "minimind_scratch.model.ScratchCausalLM"
|
||
|
|
}
|
||
|
|
}
|