NotAHorse123
commited on
Commit
•
054a3ef
1
Parent(s):
1ff1a45
Upload FalconForCausalLM
Browse files- config.json +29 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
|
3 |
+
"alibi": false,
|
4 |
+
"apply_residual_connection_post_layernorm": false,
|
5 |
+
"architectures": [
|
6 |
+
"FalconForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bias": false,
|
10 |
+
"bos_token_id": 11,
|
11 |
+
"eos_token_id": 11,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 4544,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"model_type": "falcon",
|
17 |
+
"multi_query": true,
|
18 |
+
"n_head": 71,
|
19 |
+
"n_layer": 32,
|
20 |
+
"new_decoder_architecture": false,
|
21 |
+
"num_attention_heads": 71,
|
22 |
+
"num_hidden_layers": 32,
|
23 |
+
"num_kv_heads": 71,
|
24 |
+
"parallel_attn": true,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.31.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 65024
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.31.0"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e3eb3142f0cb639b3dba5bbe80a74ddd571efdbe6b77aab08b83b9cf363fbed
|
3 |
+
size 2661665739
|