model annealed to lr 0
Browse files- config.json +1 -1
- pytorch_model.bin +1 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"d_model": 4096,
|
| 15 |
"embedding_dropout": 0.0,
|
| 16 |
"embedding_size": 50304,
|
| 17 |
-
"eos_token_id":
|
| 18 |
"flash_attention": true,
|
| 19 |
"include_bias": false,
|
| 20 |
"init_cutoff_factor": null,
|
|
|
|
| 14 |
"d_model": 4096,
|
| 15 |
"embedding_dropout": 0.0,
|
| 16 |
"embedding_size": 50304,
|
| 17 |
+
"eos_token_id": 50279,
|
| 18 |
"flash_attention": true,
|
| 19 |
"include_bias": false,
|
| 20 |
"init_cutoff_factor": null,
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27552427238
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c691ecdf9ec32368e950af49421a699e321b6efad9d21387011c0ba9e985706f
|
| 3 |
size 27552427238
|
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"eos_token": "||
|
| 3 |
"pad_token": "<|padding|>"
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eos_token": "<|endoftext|>",
|
| 3 |
"pad_token": "<|padding|>"
|
| 4 |
}
|
tokenizer_config.json
CHANGED
|
@@ -226,7 +226,7 @@
|
|
| 226 |
}
|
| 227 |
},
|
| 228 |
"clean_up_tokenization_spaces": true,
|
| 229 |
-
"eos_token": "||
|
| 230 |
"max_length": null,
|
| 231 |
"model_max_length": 1000000000000000019884624838656,
|
| 232 |
"pad_token": "<|padding|>",
|
|
|
|
| 226 |
}
|
| 227 |
},
|
| 228 |
"clean_up_tokenization_spaces": true,
|
| 229 |
+
"eos_token": "<|endoftext|>",
|
| 230 |
"max_length": null,
|
| 231 |
"model_max_length": 1000000000000000019884624838656,
|
| 232 |
"pad_token": "<|padding|>",
|