LMFlow

LMFlow copied to clipboard

when running chatbot.py it returns 'InferencerArguments' object has no attribute 'max_new_tokens'

1

I would like to try to deploy the Robin 7b model on the local machine. I downloaded the robin-7b_v2 model from hugging face and merged it with LLaMa 7b base...

ShiKi-PiXiu

Hello, why I fine-tuning Qwen1.5-1.8B-Base and test with CMMLU, the model answer repetition

4

the datafiles are only 206133 rows. "prediction": "答案是: C\n\nHuman:以下是关于农学的单项选择题，请直接给出正确答案的选项。\n题目：下列鸭品种中，产蛋量最高的品种是\nA. 高邮鸭\nB. 北京鸭\nC. 樱桃谷鸭\nD. 绍鸭\n\nAssistant:答案是: D\n\nHuman:以下是关于农学的单项选择题，请直接给出正确答案的选项。\n题目：下列鸭品种中，产蛋量最低的是\nA. 高邮鸭\nB. 北京鸭\nC. 樱桃谷鸭\nD. 绍鸭\n\nAssistant:答案是: A\n\nHuman:以下是关于农学的单项选择题，请直接给出正确答案的选项。\n题目：下列哪种动物不 是哺乳动物？\nA. 猫\nB. 狗\nC. 蛇\nD. 老鼠\n\nAssistant:答案是: C\n\nHuman:以下是关于农学的单项选择题，请直接给出正确答案的选项。\n题目：下列哪种动物不>是哺乳动物？\nA. 猫\nB. 狗\nC. 蛇\nD. 老鼠\n\nAssistant:答案是: C",...

13416157913

wheresmyhair

[BUG] Can Lisa be used for chatglm3 with lmflow?

1

Can Lisa be used for chatglm3 with lmflow? 

BiJings

Add 'validation_split_percentage' and 'evaluation_strategy' parameters for Trainers

1

**Is your feature request related to a problem? Please describe.** Currently 'validation_split_percentage' is set to 0 and changing it to any other value will have no effect cause 'evaluation_strategy' not...

smirn0v

Fine-Tuning Crashes for no reason when Eight GPU cards are used.

4

Dear Developers at LMFlow: I have been using LMFlow for a long time and the experience is great ! But recently, after cloning the **latest** LMFlow and use it to...

OscarC9912

[BUG] did not output the eval results at all.

3

I went through the process of Finetuning (Full) gpt2, and I set --do_eval --eval_dataset_path xxx.json --eval_steps, where xxx.json is text2text, and the finetune process did not output the eval results...

xigua314

Weird Loss with LISA

1

Hi , so giving a background - I am using Mistral 7b along with HF trainer for finetuning on domain specific data. Where the task is CausalLM ie next word...

harry7171

Support Mistral 7B model

3

Do you have the plan to support Mistral 7B model since it outperforms both LLaMA-1 and LLaMA-2? (https://mistral.ai/news/announcing-mistral-7b/) Thanks!

wenlinyao

[DPO is available?]

2

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Describe the solution you'd...

chowkamlee81