|
|
--- |
|
|
license: mit |
|
|
--- |
|
|
|
|
|
``` |
|
|
|
|
|
All weights were set as zero. |
|
|
|
|
|
for name, param in model.named_parameters(): |
|
|
param.data = torch.zeros_like(param.data) |
|
|
|
|
|
This model is not fit to use for pretraining. |
|
|
|
|
|
|
|
|
cf. |
|
|
When initializing to start pretraining, weights should be set to random values. |
|
|
|
|
|
from transformers import AutoConfig, AutoModelForCausalLM |
|
|
config = AutoConfig.from_pretrained("stpete2/qwen-1.5b-zero”) |
|
|
model = AutoModelForCausalLM.from_config(config) |
|
|
|
|
|
|
|
|
``` |
|
|
|
|
|
``` |
|
|
{ |
|
|
"architectures": [ |
|
|
"Qwen2ForCausalLM" |
|
|
], |
|
|
"attention_dropout": 0.0, |
|
|
"bos_token_id": 151643, |
|
|
"eos_token_id": 151643, |
|
|
"hidden_act": "silu", |
|
|
"hidden_size": 1536, |
|
|
"initializer_range": 0.02, |
|
|
"intermediate_size": 8960, |
|
|
"max_position_embeddings": 131072, |
|
|
"max_window_layers": 21, |
|
|
"model_type": "qwen2", |
|
|
"num_attention_heads": 12, |
|
|
"num_hidden_layers": 28, |
|
|
"num_key_value_heads": 2, |
|
|
"rms_norm_eps": 1e-06, |
|
|
"rope_scaling": null, |
|
|
"rope_theta": 10000, |
|
|
"sliding_window": 4096, |
|
|
"tie_word_embeddings": false, |
|
|
"torch_dtype": "float32", |
|
|
"transformers_version": "4.51.1", |
|
|
"use_cache": true, |
|
|
"use_mrope": false, |
|
|
"use_sliding_window": false, |
|
|
"vocab_size": 151936 |
|
|
} |
|
|
|
|
|
``` |
