Upload model
Browse files- config.json +23 -21
- generation_config.json +2 -2
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,30 +1,32 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"eos_token_id": 0,
|
11 |
-
"hidden_act": "gelu",
|
12 |
-
"hidden_dropout": 0.0,
|
13 |
-
"hidden_size": 512,
|
14 |
"initializer_range": 0.02,
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.40.0.dev0",
|
27 |
"use_cache": true,
|
28 |
-
"use_parallel_residual": true,
|
29 |
"vocab_size": 50309
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "cerebras/Cerebras-GPT-111M",
|
3 |
+
"activation_function": "gelu",
|
4 |
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.0,
|
10 |
+
"eos_token_id": 50256,
|
|
|
|
|
|
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_embd": 768,
|
15 |
+
"n_head": 12,
|
16 |
+
"n_inner": 3072,
|
17 |
+
"n_layer": 10,
|
18 |
+
"n_positions": 2048,
|
19 |
+
"reorder_and_upcast_attn": false,
|
20 |
+
"resid_pdrop": 0.0,
|
21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.40.0.dev0",
|
30 |
"use_cache": true,
|
|
|
31 |
"vocab_size": 50309
|
32 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
"transformers_version": "4.40.0.dev0"
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
"transformers_version": "4.40.0.dev0"
|
6 |
}
|
model.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:c8434e0ab9cb8adf28c8ebe88eeb8a3d2926091968396cf85f7dbf6c57c5b082
|
3 |
+
size 444374240
|