Upload GPTNeoXForCausalLM
Browse files- config.json +4 -4
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"GPTNeoXForCausalLM"
|
| 5 |
],
|
|
@@ -15,11 +15,11 @@
|
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 2048,
|
| 17 |
"model_type": "gpt_neox",
|
| 18 |
-
"num_attention_heads":
|
| 19 |
-
"num_hidden_layers":
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"rope_scaling": {
|
| 22 |
-
"factor":
|
| 23 |
"type": "dynamic"
|
| 24 |
},
|
| 25 |
"rotary_emb_base": 10000,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "cleaner_model_v3.pth",
|
| 3 |
"architectures": [
|
| 4 |
"GPTNeoXForCausalLM"
|
| 5 |
],
|
|
|
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 2048,
|
| 17 |
"model_type": "gpt_neox",
|
| 18 |
+
"num_attention_heads": 8,
|
| 19 |
+
"num_hidden_layers": 16,
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"rope_scaling": {
|
| 22 |
+
"factor": 4.0,
|
| 23 |
"type": "dynamic"
|
| 24 |
},
|
| 25 |
"rotary_emb_base": 10000,
|
pytorch_model.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:aa6982df9809cd158332088ff1630a64b071a7d98daf6da1d4aa909ab2ec0ff9
|
| 3 |
+
size 4047197149
|