-
Hi,
Are there any plans to allow conversion of seq2seq translation model as opus-mt (MarianMT model type)?
-
Hi,
Many thanks for releasing this library for using LLMs! We just have two quick questions about models in this library.
1. Could we know if there are any models that are good for text classif…
-
Hi,when I use the script to fine-tune fastchat-t5-3b-v1.0 with Lora:
```
CUDA_VISIBLE_DEVICES=3 python fastchat/train/train_lora_t5.py \
--model_name_or_path /fastchat-t5-3b-v1.0 \
--lora…
-
Loading settings from /content/fine_tune/config/config_file.toml...
/content/fine_tune/config/config_file
You are using the default legacy behaviour of the . This is expected, and simply means that …
-
There's small nuances in how the dynamo runners benchmark models that can make certain torchbench models fail
Some models might be explicitly skipped, others might fail because of some dtype conve…
-
Please add examples using local open-source models, like llama or chatGLM. Thanks
-
把模型换成了llama,显示没有chat()函数。就是在llm.py文件中,有一段代码: response, _ = self.model.chat(
self.tokenizer,
prompt,
history=self.history,
max_length=self.max_token,…
-
Hi,
I am trying to run some LLMs (currently trying openai models) on MMLU. My first question is which configuration is the standard setup (5 shot without CoT)? What does flan mean in some of the c…
-
https://github.com/ELS-RD/transformer-deploy/blob/main/demo/generative-model/gpt2.ipynb
In this notebook, when you tested cache feature, I think you should use `generate` function rather than `forw…
-