Create hypothetical config.json
Browse files- config.json +28 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MegatronForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"eos_token_id": 3,
|
| 9 |
+
"hidden_act": "relu2",
|
| 10 |
+
"hidden_size": 18432,
|
| 11 |
+
"initializer_range": 0.0063,
|
| 12 |
+
"intermediate_size": 73728,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "megatron",
|
| 15 |
+
"num_attention_heads": 96,
|
| 16 |
+
"num_hidden_layers": 96,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"partial_rotary_factor": 0.5,
|
| 22 |
+
"rope_theta":10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.40.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 260000
|
| 28 |
+
}
|