Upload GPTNeoXForCausalLM
Browse files- config.json +2 -2
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model.safetensors.index.json +2 -14
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
@@ -27,7 +27,7 @@
|
|
27 |
"rotary_pct": 0.5,
|
28 |
"tie_word_embeddings": false,
|
29 |
"torch_dtype": "float32",
|
30 |
-
"transformers_version": "4.
|
31 |
"use_cache": true,
|
32 |
"use_parallel_residual": true,
|
33 |
"vocab_size": 50281
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "jtatman/pythia-delphi-suboptimal",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
|
|
27 |
"rotary_pct": 0.5,
|
28 |
"tie_word_embeddings": false,
|
29 |
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.42.3",
|
31 |
"use_cache": true,
|
32 |
"use_parallel_residual": true,
|
33 |
"vocab_size": 50281
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 0,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 0,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.42.3"
|
7 |
}
|
model-00001-of-00002.safetensors
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:c10fabe7cff8e9f31da5ef1b73d8c999007f3561bfc2c933af333402a75d4b08
|
3 |
+
size 4064201824
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"embed_out.weight": "model-00002-of-00002.safetensors",
|
@@ -30,18 +30,6 @@
|
|
30 |
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
31 |
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
32 |
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
33 |
-
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
|
34 |
-
"gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
|
35 |
-
"gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
|
36 |
-
"gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
|
37 |
-
"gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
38 |
-
"gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
39 |
-
"gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
40 |
-
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
|
41 |
-
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
42 |
-
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
43 |
-
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
44 |
-
"gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
45 |
-
"gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
|
46 |
}
|
47 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 5711806464
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"embed_out.weight": "model-00002-of-00002.safetensors",
|
|
|
30 |
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
|
31 |
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
32 |
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
33 |
+
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|
35 |
}
|