add mistral changes
Browse files- config.json +3 -8
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_num_labels": 1,
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -9,13 +8,7 @@
|
|
| 9 |
"embd_pdrop": 0.1,
|
| 10 |
"eos_token_id": 50256,
|
| 11 |
"gradient_checkpointing": false,
|
| 12 |
-
"id2label": {
|
| 13 |
-
"0": "LABEL_0"
|
| 14 |
-
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"label2id": {
|
| 17 |
-
"LABEL_0": 0
|
| 18 |
-
},
|
| 19 |
"layer_norm_epsilon": 1e-05,
|
| 20 |
"model_type": "gpt2",
|
| 21 |
"n_ctx": 1024,
|
|
@@ -25,7 +18,9 @@
|
|
| 25 |
"n_layer": 48,
|
| 26 |
"n_positions": 1024,
|
| 27 |
"output_past": true,
|
|
|
|
| 28 |
"resid_pdrop": 0.1,
|
|
|
|
| 29 |
"scale_attn_weights": true,
|
| 30 |
"summary_activation": null,
|
| 31 |
"summary_first_dropout": 0.1,
|
|
@@ -39,7 +34,7 @@
|
|
| 39 |
}
|
| 40 |
},
|
| 41 |
"torch_dtype": "float32",
|
| 42 |
-
"transformers_version": "4.
|
| 43 |
"use_cache": true,
|
| 44 |
"vocab_size": 32768
|
| 45 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_function": "gelu_new",
|
| 3 |
"architectures": [
|
| 4 |
"GPT2LMHeadModel"
|
|
|
|
| 8 |
"embd_pdrop": 0.1,
|
| 9 |
"eos_token_id": 50256,
|
| 10 |
"gradient_checkpointing": false,
|
|
|
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 1024,
|
|
|
|
| 18 |
"n_layer": 48,
|
| 19 |
"n_positions": 1024,
|
| 20 |
"output_past": true,
|
| 21 |
+
"reorder_and_upcast_attn": true,
|
| 22 |
"resid_pdrop": 0.1,
|
| 23 |
+
"scale_attn_by_layer_idx": true,
|
| 24 |
"scale_attn_weights": true,
|
| 25 |
"summary_activation": null,
|
| 26 |
"summary_first_dropout": 0.1,
|
|
|
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.11.0.dev0",
|
| 38 |
"use_cache": true,
|
| 39 |
"vocab_size": 32768
|
| 40 |
}
|
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:f700cb9a50ef29578ed0b7d885e8b49208fbca9bdb9247ba9852ea6866d92e8b
|
| 3 |
+
size 6169094681
|