Commit
•
29a9082
1
Parent(s):
8080b33
Upload model
Browse files- config.json +25 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/local/home/alon_albalak/gpt-neox/outputs/1B_ods_smoothed_mean_mixed_minibatches_original_weights_init_05smoothing_seed42/global_step100000/hf_model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXModel"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 0,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 8192,
|
| 12 |
+
"layer_norm_eps": 1e-05,
|
| 13 |
+
"max_position_embeddings": 1024,
|
| 14 |
+
"model_type": "gpt_neox",
|
| 15 |
+
"num_attention_heads": 16,
|
| 16 |
+
"num_hidden_layers": 16,
|
| 17 |
+
"rotary_emb_base": 10000,
|
| 18 |
+
"rotary_pct": 0.25,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.24.0",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"use_parallel_residual": true,
|
| 24 |
+
"vocab_size": 50304
|
| 25 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d64e2ad6637118c85c83d004db457b473cf94d2af44b9e48a61ccdca23bc2d9
|
| 3 |
+
size 3651891158
|