-
Hi. Thanks for the great work. I tried to prepend and just add the
```
import transformers
from llava.cca_utils.cca import llamaforcausallm_forward, cca_forward
transformers.models.llama.LlamaFo…
-
Hi, thanks for developing such a comprehensive tool for using sequence models.
I was wondering where I could find the set of methods I should include to be able to use your functions on a model th…
-
Current our tokenizers and packer layers (`StartEndPacker` and `MultiSegmentPacker`), take a single `sequence_length` property. If it is set, outputs will be dense and padded to that length.
In rea…
-
# Description:
Hello! I appreciate the excellent work on benchmarking Performer and Longformer against the base Transformer. I’d like to propose the implementation of additional efficient Transformer…
-
### 🚀 The feature, motivation and pitch
Consider implementing BFloat16 addition/subtraction operations with stochastic rounding, as it is critical for training large models with the BFloat16 optimi…
-
### How would you like to use vllm
I would like to pass multiple LoRA modules to the vLLM engine, but currently I'm receiving error while parsing the `lora_modules` property.
The `LoRAParserActi…
-
### Odoo Version
- [ ] 15.0
- [ ] 16.0
- [X] 17.0
- [ ] Other (specify)
### Steps to Reproduce
I encountered an error when upgrading the database.
This error is because the `fname` does not exist …
-
### Title
Document Ranking with a Pretrained Sequence-to-Sequence Model
### Team Name
Team DSSM
### Email
202311022@daiict.ac.in
### Team Member 1 Name
Pratham Patel
### Team M…
-
### System Info
container built on 24th of october:
including
pip install tqdm
pip install torch
pip install torchvision
pip install transformers
pip install deepspeed==0.15.2
pip…
-
I run triton with tensorrtllm. But when i give long text to llm, triton returns a long array of zeros named output_log_probs in every token. If my text be longer than some number, the request not work…