Fix bos/eos token ids to match the Llama tokenizer (1/2)
Browse filesFixes huggingface/optimum-executorch#28.
The bundled `LlamaTokenizer` uses the standard Llama special tokens (`<s>`=1, `</s>`=2), but `config.json` and `generation_config.json` declared `bos_token_id=0, eos_token_id=1`. optimum-executorch exports `get_bos_id`/`get_eos_id` from the config, so the `.pte` carried 0/1 and `ExecuTorchModelForCausalLM.text_generation` correctly rejected the mismatch:
`ValueError: The tokenizer's bos_token_id=1 must be the same as the model's bos_token_id=0.`
This sets `bos_token_id=1, eos_token_id=2` in both files. No weights or tokenizer files changed. A companion PR updates the `executorch` revision (configs + regenerated `model.pte`).
- config.json +2 -2
- generation_config.json +2 -2
config.json
CHANGED
|
@@ -5,8 +5,8 @@
|
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id":
|
| 9 |
-
"eos_token_id":
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 16,
|
| 12 |
"initializer_range": 0.02,
|
|
|
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 16,
|
| 12 |
"initializer_range": 0.02,
|
generation_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
-
"eos_token_id":
|
| 5 |
"pad_token_id": -1,
|
| 6 |
"transformers_version": "4.38.0.dev0"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
"pad_token_id": -1,
|
| 6 |
"transformers_version": "4.38.0.dev0"
|
| 7 |
}
|