MerziaAdamjee
commited on
Commit
•
a2442fd
1
Parent(s):
abe73ea
Upload OPTForCausalLM
Browse files- config.json +29 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-iml-1.3b",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"OPTForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 2,
|
10 |
+
"do_layer_norm_before": true,
|
11 |
+
"dropout": 0.1,
|
12 |
+
"enable_bias": true,
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"ffn_dim": 8192,
|
15 |
+
"hidden_size": 2048,
|
16 |
+
"init_std": 0.02,
|
17 |
+
"layer_norm_elementwise_affine": true,
|
18 |
+
"layerdrop": 0.0,
|
19 |
+
"max_position_embeddings": 2048,
|
20 |
+
"model_type": "opt",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 24,
|
23 |
+
"pad_token_id": 1,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.33.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50272,
|
28 |
+
"word_embed_proj_dim": 2048
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.33.2"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d76ed8305619803c26909d8ce216ee6b182f8ab67d3e7902136d46bbe1ee93e
|
3 |
+
size 5263164789
|