63000
Browse files- config.json +35 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTBigCodeLMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_softmax_in_fp32": true,
|
| 7 |
+
"attention_window_size": 8192,
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"head_groups": 2,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"layer_norm_epsilon": 1e-05,
|
| 15 |
+
"model_type": "gpt_bigcode",
|
| 16 |
+
"n_embd": 3072,
|
| 17 |
+
"n_head": 24,
|
| 18 |
+
"n_inner": 12288,
|
| 19 |
+
"n_layer": 30,
|
| 20 |
+
"n_positions": 16384,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"rotary_embedding_scale": -13.81551,
|
| 23 |
+
"scale_attention_softmax_in_fp32": true,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"transformers_version": "4.34.1",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"use_position_embeddings": false,
|
| 33 |
+
"use_rotary_embeddings": true,
|
| 34 |
+
"vocab_size": 49152
|
| 35 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00cf22118fee8237c8fff0d6e1f95dc1d6c79332a045b91b5bd48a284ee457bb
|
| 3 |
+
size 23636934338
|