-
Could you upload a pre trained model for those with less powerful GPUs, You could upload to Hugging face. Thanks. I just want a ChatGPT Alternative that can run locally and have a chat with the model …
-
AutoModelForCausalLM 中class没有chatglm你是如何解决的呢
-
感谢工作!
请问这里 ppo model 为什么要接一个valuehead 呢?
https://github.com/beyondguo/LLM-Tuning/blob/ed68123815bc0add9ad2d7ddc2a48dc584db2c94/RLHF/rl_training.py#L185C1-L185C11
这个head好像随机初始化的?
-
Great work and repo.
Whilst I'm aware the actual training likely follows general LLM training scripts/flow. It would be nice to see the training scripts. Is there any plan to upload?
-
你好,请教一下。
RLHF 里面的 model_name 对应的目录是不是要把 sft 生成的 .bin 和原始的底座模型合并后地址?
-
setting as follow:
`
deepspeed --master_port 12346 main.py \
--data_path yitingxie/rlhf-reward-datasets \
--data_split 2,4,4 \
--actor_model_name_or_path $ACTOR_MODEL_PATH \
--crit…
-
I didn't find a forum in this repo, so I put this in an issue instead; I hope that is OK.
Just for fun, I tried this on GPT4. I copied your example into a graphvis node list and just fed it into th…
-
Should be quite easy to add for someone who knows the codebase. The biggest problem might be a new dataset format.
Don't expect I need to link this but it's pretty nice implementation of the loss:
…
-
Lots of multilingual datasets listed here https://docs.google.com/spreadsheets/d/1qf0iYejG-9RgEEi13qB_SK_178-eNaeJDmSDNSj260A/edit?gid=1875159366#gid=1875159366 from https://blog.voyageai.com/2024/06/…
-
Hi authors,
First of all, thanks for your great work on LLaMA-2! This is an impressive work for open source large language models!
I have a question about section 3.1 in the paper, specifically …