quantumaikr
commited on
Commit
•
daf1bd1
1
Parent(s):
61e4d9b
Upload PlanktonForCausalLM
Browse files- config.json +27 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"PlanktonForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 0,
|
6 |
+
"eos_token_id": 1,
|
7 |
+
"hidden_act": "silu",
|
8 |
+
"hidden_size": 1500,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 3600,
|
11 |
+
"max_position_embeddings": 2000,
|
12 |
+
"model_type": "PLANKTON",
|
13 |
+
"num_attention_heads": 15,
|
14 |
+
"num_hidden_layers": 15,
|
15 |
+
"num_key_value_heads": 15,
|
16 |
+
"pad_token_id": 3,
|
17 |
+
"pretraining_tp": 1,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 10000.0,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.33.0",
|
24 |
+
"unk_token_id": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 42000
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.33.0"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5544c74ae4feabe6ba93a009627c06435463b716659b8ab06f74597e929b4d33
|
3 |
+
size 2016228725
|