-
There are two issues when reproducing the experiments.
## baseline (P-zero)
The P-zero acc of LLaMA2 on KAssess is only 35.22%, much lower than the paper's 50.00%.
(`sampling_params = SamplingPara…
-
Hi. I have finetune the _Helsinki-NLP/opus-mt-zh-vi_ model for translating Chinese to Vietnamese. When I convert the model to ctranslate2, the performance is decrease (from 32 sacrebleu with transform…
-
NLTK version 3.8.2 changed the data format of the tokenizers from pickle to text files in order to patch a vulnerability (CVE-2024-39705).
Here's the PR in the nltk repo:
https://github.com/nltk/n…
-
[ ] I checked the [documentation](https://docs.ragas.io/) and related resources and couldn't find an answer to my question.
** Facing error with using Langchain wrapped hugging face models**
I am …
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Environment
```markdown
- Milvus version:zhengbuqian-doc-in-restful-d174d05-20241010
- Deployment mode(standa…
-
### System Info
peft==0.13.2
accelerate==1.0.1
torch==2.4.0
peft_config
```python
peft_config = PromptTuningConfig(
task_type=TaskType.CAUSAL_LM,
prompt_tuning_init=PromptTuningI…
-
### What is the bug?
I am using text_chunking and text_embedding processor to ingest documents into an index. The [text_chunking search example](https://opensearch.org/docs/latest/search-plugins/text…
-
Read the blog post here: https://dzone.com/articles/using-natural-nlp-module
Wondering if `Punkt sentence segmentation` as been added? I don't seet iin README. If not, I can take a crack at it.
Or …
-
Is there any way to adjust tokenizer parameters that how the tokenizer(?) divides the sentences? May I ask how sentence-splitting is done when the program is configured to (being~by) feed generator it…
-
Hi! I followed the instructions for fine-tuning my corpus and (I think) managed to do so successfully after days of debugging. I have A LOT of implementation questions and the following is half-guide,…