Commit
•
8020c85
1
Parent(s):
9f230b4
Upload FlaxOPTForCausalLM
Browse files- config.json +32 -0
- flax_model.msgpack +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/mini",
|
| 3 |
+
"_remove_final_layer_norm": false,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"OPTForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"bias": false,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"do_layer_norm_before": true,
|
| 13 |
+
"dropout": 0.1,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"ffn_dim": 3072,
|
| 16 |
+
"hidden_size": 768,
|
| 17 |
+
"init_std": 0.02,
|
| 18 |
+
"layer_norm_elementwise_affine": false,
|
| 19 |
+
"layerdrop": 0.0,
|
| 20 |
+
"learned_embeddings": true,
|
| 21 |
+
"max_position_embeddings": 2048,
|
| 22 |
+
"model_type": "opt",
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_layers": 12,
|
| 25 |
+
"pad_token_id": 1,
|
| 26 |
+
"scale_embeddings": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.23.1",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50000,
|
| 31 |
+
"word_embed_proj_dim": 768
|
| 32 |
+
}
|
flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f25f8049ff43525fcf2c82733a0917f5befe46baa98508c982b2384bce438e49
|
| 3 |
+
size 500128449
|