-
We need to convert keras.io examples to work with Keras 3.
This involves two stages:
## Stage 1: tf.keras backwards compatibility check
Keras 3 is intended as a drop-in replacement for tf.ker…
-
Hi,
thank you for building this amazing repo. My purpose is to train on msmarco a ColBERT model using `distilbert` as backbone.
I took your script [`knowledge_distillation.py`](https://github.com/…
-
The code below leaks memory when running on OCaml 5 trunk, but by not starting the domain it stops leaking memory.
```ocaml
let _domain =
Domain.spawn (fun () ->
let rec loop () = loop (…
-
## Abstract
- present the `Insertion Transformer`, an iterative and partially autoregressive model for sequence generation based on insertion operations
- can generate with an arbitrary ordering
…
-
### Checklist
- I have searched related issues but cannot get the expected help.
- I have read related documents and don't know what to do.
### Describe the question you meet
I want to…
-
**场景**：使用BGE-M3进行finetune，数据文件.jsonl 含有158000行记录，每行记录一个query，pos列表的长度为1，neg列表的长度为15。
**异常报错**：
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS envi…
-
Embedding Guile Scheme
M
gnu guile snarf
Edit
I'm afraid I don't have enough context to fully understand your query "gnu guile snarf". However, let me provide some potentially relevant informatio…
-
I got GPU OOM error when trying to finetune embedder model on Kaggle (using GPU T4 x 2)
This is my run command (already reduce query_max_len and passage_max_len):
```
!WANDB_DISABLED=True WANDB_M…
-
I read from https://docs.larq.dev/zoo/ that the RealToBinaryNet reach 65% accuracy and reach the SOTA.
I really appreciate this and want to train the model to learn about it.
I also read the code a…
-
## **Summary**
This is a design discussion RFC for contributing some device-agnostic compression algorithms, like the post training quantization(QDQ quant format) and structural sparsity supported …