Instructions to use Archit001a/model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Archit001a/model with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForNextSentencePrediction tokenizer = AutoTokenizer.from_pretrained("Archit001a/model") model = AutoModelForNextSentencePrediction.from_pretrained("Archit001a/model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- config.json +18 -31
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,39 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"reorder_and_upcast_attn": false,
|
| 21 |
-
"resid_pdrop": 0.1,
|
| 22 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
-
"scale_attn_weights": true,
|
| 24 |
-
"summary_activation": null,
|
| 25 |
-
"summary_first_dropout": 0.1,
|
| 26 |
-
"summary_proj_to_labels": true,
|
| 27 |
-
"summary_type": "cls_index",
|
| 28 |
-
"summary_use_proj": true,
|
| 29 |
-
"task_specific_params": {
|
| 30 |
-
"text-generation": {
|
| 31 |
-
"do_sample": true,
|
| 32 |
-
"max_length": 50
|
| 33 |
-
}
|
| 34 |
-
},
|
| 35 |
"torch_dtype": "float32",
|
| 36 |
"transformers_version": "4.35.2",
|
|
|
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForNextSentencePrediction"
|
| 5 |
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.35.2",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
}
|
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 sha256:4d2d6bc8a3ace95384d7c5d6913c7a28f9f309f9e7b63d3cf0e2dd2a22de915e
|
| 3 |
+
size 437958664
|