-
### 1 from Wallace
[Combining crowd and expert labels using decision theoretic active learning](https://scholar.google.com/scholar?q=Combining+crowd+and+expert+labels+using+decision+theoretic+active+…
-
I'm trying to use DeepSpeed-Chat stage2 scripts to do rlhf with Qwen1.8b-chat model,I change some parts in dschat and main.py to load my model, the most different part is:
```
if 'Qwen' in model_nam…
-
I was using DistributedDataParallel to train a model on single machine 8 gpus. I thought by using DistributedDataParallel, memory on each gpu should be approximately the same, however, there is one gp…
-
Afaict service health is displayed as "unknown" if:
- the service does not have "request" or "page-load" type, or
- there are no Ml data for the ML job
- no ML job exists
We should add a t…
-
### Workflow
**Core mapping: Grade (from judgment) - Features (feature name 1, feature name 2, ...) - document identifier**
### Sequence Diagram
#### Step 1: Create ltr index
ltr…
-
**Describe the bug**
I am trying to SFT fine-tune the model `llava-onevision-qwen2-0_5b-ov` using the following command:
```
swift sft \
--model_type llava-onevision-qwen2-0_5b-ov \
--dat…
-
## Overview
https://github.com/foundation-model-stack/fms-hf-tuning/blob/5c09dbc9d38e9479a7f720e9d6b316243a128343/pyproject.toml#L30
## Steps to reproduce
1. Build the docker image
2. Doing …
-
Hi, I'm a computer science student based in Milan.
I want to know if I can use this library (especially, with the Python interface/wrapper) for the ranking task. I want to learn a ranking function in…
-
I am executing this code for analyzing the loss function for learning to rank. But while running this mlr I have got numbers
![screenshot 2018-02-26 23 29 43](https://user-images.githubusercontent.co…
-
你好徐老师,我使用的是windows四卡3090机器,每张显卡24G显存,因为是win平台,就写了一个bat脚本来运行
`@echo off
set CUDA_VISIBLE_DEVICES=0,1,2,3
call python supervised_finetuning.py ^
--model_type baichuan ^
--model_name_or_p…