gritlm

gritlm copied to clipboard

BUG: NotImplementedError

3

When I run the script of Training.embedding_model, a bug is occurred. How can I fix it? File /gritlm/training/run.py", line 166, in main else: raise NotImplementedError NotImplementedError

oYoungCo

Muennighoff

For document clustering, should we leave instruction blank?

3

Thanks -- I am using Grit for document embeddings that will be used to score doc-to-doc similarity. Should I add an instruction or leave it blank? Thank you, Griffin

griff4692

How to write the prompt to tell the model that it should only generate the answers based on the context?

1

Hi guys, we have tried your model for a bigger number of documents (then used in the example code) and found that the model does not suse the provided documents...

gabriead

how to do doc cache if there are multiple documents in rag?

2

generally, we will have several docs for reference while doing rag, wondering if you guys have tested this setting with doc cache?

SimonYx42

How would one go about running embedding as a service using something like vLLM?

5

I would like to run embedding as a service using something like vLLM on a Docker container on different host. How would one go about doing this?

sungkim11

About OOM During Training and Questions Regarding Attn

7

Thank you for your contribution! I have encountered some issues. 1、Full train Here is my training script: ``` CUDA_VISIBLE_DEVICES="0,5" torchrun --nproc_per_node 2 \ -m training.run \ --output_dir ./output/7-2_full \ --model_name_or_path...

Zheng-Jay

TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]

6

Thank you for your contribution. I encountered the following error when training with toy data: TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]] I read online that the following reasons may...

bo-jpg

question about emb loss

3

def __call__(self, q_reps, p_reps): if self.negatives_cross_device: # This gathers both negatives and positives. # It could likely be optimized by only gathering negatives. q_reps = self._dist_gather_tensor(q_reps) p_reps = self._dist_gather_tensor(p_reps) scores...

256785

sentence transforemr

2

Is there a way to load this through HF sentence transformer library?

drewskidang