Upload GPTNeoXForCausalLM
Browse files- config.json +3 -3
- generation_config.json +6 -0
- pytorch_model-00001-of-00002.bin +2 -2
- pytorch_model-00002-of-00002.bin +2 -2
- pytorch_model.bin.index.json +0 -0
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"bos_token_id": 0,
|
7 |
"classifier_dropout": 0.1,
|
@@ -14,7 +14,7 @@
|
|
14 |
"max_position_embeddings": 2048,
|
15 |
"model_type": "gpt_neox",
|
16 |
"num_attention_heads": 32,
|
17 |
-
"num_hidden_layers":
|
18 |
"rotary_emb_base": 10000,
|
19 |
"rotary_pct": 1.0,
|
20 |
"tie_word_embeddings": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "togethercomputer/RedPajama-INCITE-Base-3B-v1",
|
3 |
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
],
|
6 |
"bos_token_id": 0,
|
7 |
"classifier_dropout": 0.1,
|
|
|
14 |
"max_position_embeddings": 2048,
|
15 |
"model_type": "gpt_neox",
|
16 |
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
"rotary_emb_base": 10000,
|
19 |
"rotary_pct": 1.0,
|
20 |
"tie_word_embeddings": false,
|
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-00001-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18ec97b1c866f58806abe79727cebf3a63d25ade72023b5bfe68f06ff6c6b155
|
3 |
+
size 10087836117
|
pytorch_model-00002-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f03753e18e89eb52014dcdbf9ce1b44529d17e690eed0cf191868ac4a1f98d9f
|
3 |
+
size 5933604532
|
pytorch_model.bin.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|