Balkondekar Rohan Ramesh
commited on
Commit
•
e0c83e5
1
Parent(s):
f18facf
Upload model
Browse files- config.json +39 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-125m",
|
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 |
+
"attention_probs_dropout_prob": 0.0,
|
11 |
+
"bos_token_id": 2,
|
12 |
+
"custom_pipelines": {
|
13 |
+
"text-generation": {
|
14 |
+
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
|
15 |
+
"pt": "AutoModelForCausalLM"
|
16 |
+
}
|
17 |
+
},
|
18 |
+
"do_layer_norm_before": true,
|
19 |
+
"dropout": 0.1,
|
20 |
+
"enable_bias": true,
|
21 |
+
"eos_token_id": 2,
|
22 |
+
"ffn_dim": 3072,
|
23 |
+
"hidden_dropout_prob": 0.0,
|
24 |
+
"hidden_size": 768,
|
25 |
+
"init_std": 0.02,
|
26 |
+
"layer_norm_elementwise_affine": true,
|
27 |
+
"layerdrop": 0.0,
|
28 |
+
"max_position_embeddings": 2048,
|
29 |
+
"model_type": "opt",
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"pad_token_id": 1,
|
33 |
+
"prefix": "</s>",
|
34 |
+
"torch_dtype": "float16",
|
35 |
+
"transformers_version": "4.30.1",
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50272,
|
38 |
+
"word_embed_proj_dim": 768
|
39 |
+
}
|
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": "4.30.1"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f56ea4cdeff283983415da7b9b5121d12269b258e7ff5cd15b9f9b653187a9d
|
3 |
+
size 250544797
|