prasanna2003
commited on
Commit
•
f15dd29
1
Parent(s):
c935173
Upload GPTNeoXForCausalLM (#1)
Browse files- Upload GPTNeoXForCausalLM (bed4ea591dcb6782a25eb7fcc95530c0984f9939)
- config.json +26 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-160m",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": 0.1,
|
8 |
+
"eos_token_id": 0,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "gpt_neox",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"rotary_emb_base": 10000,
|
19 |
+
"rotary_pct": 0.25,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.29.2",
|
23 |
+
"use_cache": true,
|
24 |
+
"use_parallel_residual": true,
|
25 |
+
"vocab_size": 50304
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.29.2"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2209cca051e2ed6c96229b85d131638a1c0b9089e69a81a1f0c92e33fd4426b0
|
3 |
+
size 699682733
|