Training in progress, step 3
Browse files- config.json +23 -48
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,56 +1,31 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"
|
|
|
|
|
|
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
-
"attention_dropout": 0,
|
| 8 |
-
"
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
"local",
|
| 19 |
-
"global",
|
| 20 |
-
"local"
|
| 21 |
-
],
|
| 22 |
-
"attention_types": [
|
| 23 |
-
[
|
| 24 |
-
[
|
| 25 |
-
"global",
|
| 26 |
-
"local"
|
| 27 |
-
],
|
| 28 |
-
6
|
| 29 |
-
]
|
| 30 |
-
],
|
| 31 |
-
"bos_token_id": 50256,
|
| 32 |
-
"classifier_dropout": 0.1,
|
| 33 |
-
"embed_dropout": 0,
|
| 34 |
-
"eos_token_id": 50256,
|
| 35 |
-
"gradient_checkpointing": false,
|
| 36 |
-
"hidden_size": 768,
|
| 37 |
-
"initializer_range": 0.02,
|
| 38 |
-
"intermediate_size": null,
|
| 39 |
-
"layer_norm_epsilon": 1e-05,
|
| 40 |
"max_position_embeddings": 2048,
|
| 41 |
-
"model_type": "
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"pad_token_id":
|
| 45 |
-
"
|
| 46 |
-
"summary_activation": null,
|
| 47 |
-
"summary_first_dropout": 0.1,
|
| 48 |
-
"summary_proj_to_labels": true,
|
| 49 |
-
"summary_type": "cls_index",
|
| 50 |
-
"summary_use_proj": true,
|
| 51 |
"torch_dtype": "float32",
|
| 52 |
"transformers_version": "4.44.2",
|
| 53 |
"use_cache": true,
|
| 54 |
-
"vocab_size":
|
| 55 |
-
"
|
| 56 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/opt-350m",
|
| 3 |
+
"_remove_final_layer_norm": false,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
"architectures": [
|
| 7 |
+
"OPTForCausalLM"
|
| 8 |
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 2,
|
| 11 |
+
"do_layer_norm_before": false,
|
| 12 |
+
"dropout": 0.1,
|
| 13 |
+
"enable_bias": true,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"ffn_dim": 4096,
|
| 16 |
+
"hidden_size": 1024,
|
| 17 |
+
"init_std": 0.02,
|
| 18 |
+
"layer_norm_elementwise_affine": true,
|
| 19 |
+
"layerdrop": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"max_position_embeddings": 2048,
|
| 21 |
+
"model_type": "opt",
|
| 22 |
+
"num_attention_heads": 16,
|
| 23 |
+
"num_hidden_layers": 24,
|
| 24 |
+
"pad_token_id": 2,
|
| 25 |
+
"prefix": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"torch_dtype": "float32",
|
| 27 |
"transformers_version": "4.44.2",
|
| 28 |
"use_cache": true,
|
| 29 |
+
"vocab_size": 50272,
|
| 30 |
+
"word_embed_proj_dim": 512
|
| 31 |
}
|
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 sha256:5decd64edf138c9c3c475a6c424ac4571e764cabee572d2d285166581981d2b0
|
| 3 |
+
size 1324830880
|