update config.json vocab_size to tokenizer length
Browse files.i.e., 32000 as for high throughput in vllm there can be sampling of padded tokens which will result in error in vllm , it is an open issue here . https://github.com/vllm-project/vllm/issues/340
- config.json +1 -1
config.json
CHANGED
@@ -30,5 +30,5 @@
|
|
30 |
"torch_dtype": "float16",
|
31 |
"transformers_version": "4.38.2",
|
32 |
"use_cache": false,
|
33 |
-
"vocab_size":
|
34 |
}
|
|
|
30 |
"torch_dtype": "float16",
|
31 |
"transformers_version": "4.38.2",
|
32 |
"use_cache": false,
|
33 |
+
"vocab_size": 32000
|
34 |
}
|