-
I get the following error
"(h2ogpt) C:\Users\username\h2ogpt>python generate.py --base_model=h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3 --langchain_mode=UserData --score_model=None --load_4bit=Tr…
-
I'm trying to run the `sentiment_tuning.py` [example](https://github.com/lvwerra/trl/blob/main/examples/scripts/sentiment_tuning.py) with `accelerate` and DeepSpeed ZeRO-3, but am hitting a runtime er…
-
基座使用baichuan-13b,sft是全参数微调,rm在sft基础上lora微调,ppo启动脚本如下:
```
export CUDA_VISIBLE_DEVICES=1,2,3,4
deepspeed --num_gpus 4 --master_port=9901 src/train_bash.py \
--deepspeed deepspeed_zero3.json…
-
I've reproduced the whole StackLLaMA pipeline using the changes in #398 #399 #400
Here is the [corresponding wandb report](https://wandb.ai/mnoukhov/trl/reports/StackLLaMA-Repro--Vmlldzo0NTM1MDk2)…
-
sudo docker run \
--gpus all \
--runtime=nvidia \
--shm-size=2g \
--rm --init \
--network host \
-v /etc/passwd:/etc/passwd:ro \
-v /etc/group:/…
-
## How to Reproduce
1. Train
2. Push to Huggingface
3. Error 😢
With:
- Docker image:
- Runpod A100 80GB
Config:
```yaml
architecture:
backbone_dtype: int8
force_embedding_…
-
# 虚幻引擎5 游戏技能系统(GAS) Unreal Engine 5 Gameplay Ability System
https://docs.unrealengine.com/5.3/zh-CN/gameplay-ability-system-for-unreal-engine/
-
Reproduce:
torchrun reward_summarization.py
details:
You're using a GPT2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a metho…
-
-
Hi, I also met the same issue when I `bash run_finetune_with_lora.sh` with the `LLAMA-7b`. The following is my script and log:
```
#!/bin/bash
# Please run this script under ${project…