DistilRoBERTa config
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 536
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
Hi,
I was trying to convert DistilRoBERTa model and got the following error
ValueError: No conversion is registered for the model configuration RobertaConfig (supported configurations are: BartConfig, BertConfig, BloomConfig, CodeGenConfig, DistilBertConfig, FalconConfig, GPT2Config, GPTBigCodeConfig, GPTJConfig, GPTNeoXConfig, LlamaConfig, M2M100Config, MBartConfig, MPTConfig, MT5Config, MarianConfig, MixFormerSequentialConfig, OPTConfig, PegasusConfig, RWConfig, T5Config, WhisperConfig, XLMRobertaConfig)
I know that DistilRoBERTa is based on RobertaConfig, do we know if RobertaConfig will be supported in later version of the project?
There is support for XLM-RoBERTa which is also based on RobertaConfig I think, is there any way where I can convert DistilRoBERTa model
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the reported DistilRoBERTa conversion error and checking the current supported configuration list, especially RobertaConfig, DistilBertConfig, and XLMRobertaConfig. Determine whether an existing conversion path applies or whether RobertaConfig support is needed; done means DistilRoBERTa conversion works or the limitation is clearly documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 30/100