shadeMe-explosion
commited on
Commit
•
a33ca86
1
Parent(s):
865cda6
Add Falcon new decoder w/t alibi test model
Browse files- config.json +25 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alibi": true,
|
3 |
+
"architectures": [
|
4 |
+
"FalconForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bias": false,
|
8 |
+
"bos_token_id": 11,
|
9 |
+
"eos_token_id": 11,
|
10 |
+
"hidden_dropout": 0.0,
|
11 |
+
"hidden_size": 64,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "falcon",
|
15 |
+
"multi_query": true,
|
16 |
+
"new_decoder_architecture": true,
|
17 |
+
"num_attention_heads": 4,
|
18 |
+
"num_hidden_layers": 2,
|
19 |
+
"num_kv_heads": 2,
|
20 |
+
"parallel_attn": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.31.0.dev0",
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 1024
|
25 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 11,
|
4 |
+
"eos_token_id": 11,
|
5 |
+
"transformers_version": "4.31.0.dev0"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eccea0f2269fa8e8b2d8e160c00e7cf57415b97c3425b086ff7f9aba58b782c1
|
3 |
+
size 631210
|