tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

chore(doc): add faq when having no default chat_template (#2398)

Browse Source 
* chore(doc): add faq when having no default chat_template

* Update docs/dataset-formats/conversation.qmd

Co-authored-by: salman <salman.mohammadi@outlook.com>

* Update docs/faq.qmd

Co-authored-by: salman <salman.mohammadi@outlook.com>

---------

Co-authored-by: salman <salman.mohammadi@outlook.com>
This commit is contained in:
NanoCode012
2025-03-10 16:25:50 +07:00
committed by GitHub
parent 3b477e08a0
commit 46a045e528
2 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/dataset-formats/conversation.qmd
View File

@@ -74,6 +74,10 @@ datasets:
train_on_eos: train_on_eos:
``` ```
::: {.callout-tip}
If you receive an error like "`chat_template` choice is `tokenizer_default` but tokenizer's `chat_template` is null.", it means the tokenizer does not have a default `chat_template`. Follow the examples below instead to set a custom `chat_template`.
:::
2. Using the `gemma` chat template to override the tokenizer_config.json's chat template on OpenAI messages format, training on all assistant messages. 2. Using the `gemma` chat template to override the tokenizer_config.json's chat template on OpenAI messages format, training on all assistant messages.
```yaml ```yaml

4
docs/faq.qmd
View File

@@ -52,3 +52,7 @@ description: Frequently asked questions
**Q: The EOS/EOT token is incorrectly being masked or not being masked.** **Q: The EOS/EOT token is incorrectly being masked or not being masked.**
> A: This is because of the mismatch between `tokenizer.eos_token` and EOS/EOT token in template. Please make sure to set `eos_token` under `special_tokens` to the same EOS/EOT token as in template. > A: This is because of the mismatch between `tokenizer.eos_token` and EOS/EOT token in template. Please make sure to set `eos_token` under `special_tokens` to the same EOS/EOT token as in template.
**Q: "`chat_template` choice is `tokenizer_default` but tokenizer's `chat_template` is null. Please add a `chat_template` in tokenizer config"**
> A: This is because the tokenizer does not have a chat template. Please add a chat template in the tokenizer config. See [chat_template](dataset-formats/conversation.qmd#chat-template) for more details.