add model
Browse files- config.json +5 -5
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -12,10 +12,10 @@
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 1024,
|
| 15 |
-
"n_embd":
|
| 16 |
-
"n_head":
|
| 17 |
"n_inner": null,
|
| 18 |
-
"n_layer":
|
| 19 |
"n_positions": 1024,
|
| 20 |
"reorder_and_upcast_attn": false,
|
| 21 |
"resid_pdrop": 0.1,
|
|
@@ -32,7 +32,7 @@
|
|
| 32 |
}
|
| 33 |
},
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
-
"transformers_version": "4.
|
| 36 |
"use_cache": true,
|
| 37 |
"vocab_size": 50257
|
| 38 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "./output-small",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 1024,
|
| 16 |
+
"n_head": 16,
|
| 17 |
"n_inner": null,
|
| 18 |
+
"n_layer": 24,
|
| 19 |
"n_positions": 1024,
|
| 20 |
"reorder_and_upcast_attn": false,
|
| 21 |
"resid_pdrop": 0.1,
|
|
|
|
| 32 |
}
|
| 33 |
},
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.17.0",
|
| 36 |
"use_cache": true,
|
| 37 |
"vocab_size": 50257
|
| 38 |
}
|
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 sha256:0673e95a59b9d45ac4e808d0834269fb566aee44410da32e70206d7c44834b7e
|
| 3 |
+
size 1444577689
|