Upload config.json with huggingface_hub
Browse files- config.json +36 -0
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_config": {
|
| 3 |
+
"n_layer": 2,
|
| 4 |
+
"d_model": 4096,
|
| 5 |
+
"n_ctx": 512,
|
| 6 |
+
"d_head": 16,
|
| 7 |
+
"d_mlp": 16384,
|
| 8 |
+
"vocab_size": 4096,
|
| 9 |
+
"use_rms_norm": true,
|
| 10 |
+
"tie_embeddings": false,
|
| 11 |
+
"use_positional_embeddings": false,
|
| 12 |
+
"use_bigram_table": false,
|
| 13 |
+
"use_attention_sinks": true,
|
| 14 |
+
"activation": "gelu",
|
| 15 |
+
"dropout": 0.0,
|
| 16 |
+
"use_bias": true
|
| 17 |
+
},
|
| 18 |
+
"sparsity_config": {
|
| 19 |
+
"enable_weight_sparsity": true,
|
| 20 |
+
"target_l0_fraction": 0.002,
|
| 21 |
+
"enable_activation_sparsity": true,
|
| 22 |
+
"activation_topk_fraction": 0.25
|
| 23 |
+
},
|
| 24 |
+
"bridges_config": {
|
| 25 |
+
"encoder_afrac": 0.25,
|
| 26 |
+
"n_layers": 2,
|
| 27 |
+
"d_dense": "jacobcd52/ss_d128_f1",
|
| 28 |
+
"d_sparse": 4096
|
| 29 |
+
},
|
| 30 |
+
"training_config": {
|
| 31 |
+
"total_tokens": 2000000000,
|
| 32 |
+
"batch_size": 32,
|
| 33 |
+
"dataset_name": "data/simplestories-tokenized",
|
| 34 |
+
"tokenizer_name": "SimpleStories/SimpleStories-1.25M"
|
| 35 |
+
}
|
| 36 |
+
}
|