Upload GPTNeoXForCausalLM
Browse files- config.json +3 -3
- pytorch_model.bin +3 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
@@ -14,11 +14,11 @@
|
|
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,
|
21 |
-
"torch_dtype": "
|
22 |
"transformers_version": "4.29.2",
|
23 |
"use_cache": true,
|
24 |
"use_parallel_residual": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Dampish/Stellar6-4B-V0",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
|
|
14 |
"max_position_embeddings": 2048,
|
15 |
"model_type": "gpt_neox",
|
16 |
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 46,
|
18 |
"rotary_emb_base": 10000,
|
19 |
"rotary_pct": 1.0,
|
20 |
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float16",
|
22 |
"transformers_version": "4.29.2",
|
23 |
"use_cache": true,
|
24 |
"use_parallel_residual": false,
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a490d1dfe2a30b534efc5da947cbdcdf3152208e008ae0b250a837a9014a743
|
3 |
+
size 8109364665
|