Upload model
Browse files- config.json +6 -6
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "gpt2",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -12,11 +11,12 @@
|
|
| 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,
|
| 22 |
"scale_attn_by_inverse_layer_idx": false,
|
|
@@ -33,7 +33,7 @@
|
|
| 33 |
}
|
| 34 |
},
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
-
"transformers_version": "4.
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
"GPT2LMHeadModel"
|
|
|
|
| 11 |
"layer_norm_epsilon": 1e-05,
|
| 12 |
"model_type": "gpt2",
|
| 13 |
"n_ctx": 1024,
|
| 14 |
+
"n_embd": 1600,
|
| 15 |
+
"n_head": 25,
|
| 16 |
"n_inner": null,
|
| 17 |
+
"n_layer": 48,
|
| 18 |
"n_positions": 1024,
|
| 19 |
+
"output_past": true,
|
| 20 |
"reorder_and_upcast_attn": false,
|
| 21 |
"resid_pdrop": 0.1,
|
| 22 |
"scale_attn_by_inverse_layer_idx": false,
|
|
|
|
| 33 |
}
|
| 34 |
},
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.51.3",
|
| 37 |
"use_cache": true,
|
| 38 |
+
"vocab_size": 32768
|
| 39 |
}
|
generation_config.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
"eos_token_id": 50256,
|
| 5 |
-
"transformers_version": "4.
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
}
|