danielhanchen
commited on
Commit
•
cf5bb69
1
Parent(s):
7add248
Upload config
Browse files- README.md +1 -1
- config.json +3 -1
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
-
license: llama3
|
5 |
library_name: transformers
|
|
|
6 |
tags:
|
7 |
- unsloth
|
8 |
- transformers
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
library_name: transformers
|
5 |
+
license: llama3
|
6 |
tags:
|
7 |
- unsloth
|
8 |
- transformers
|
config.json
CHANGED
@@ -17,13 +17,15 @@
|
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
|
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
"rope_scaling": null,
|
23 |
"rope_theta": 500000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
-
"transformers_version": "4.
|
|
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 128256
|
29 |
}
|
|
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 128255,
|
21 |
"pretraining_tp": 1,
|
22 |
"rms_norm_eps": 1e-05,
|
23 |
"rope_scaling": null,
|
24 |
"rope_theta": 500000.0,
|
25 |
"tie_word_embeddings": false,
|
26 |
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.44.0",
|
28 |
+
"unsloth_version": "2024.8",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 128256
|
31 |
}
|