-
Which LLaMA 7b model was used?
Is it available on Hugging face?
Thank you. I am trying to reproduce your success
-
Hi all,
Sorry Im new to hugging face/llama/ Alpaca, i encounter this error when run the finetune.py
Loading checkpoint shards: 100%|██████████| 33/33 [00:10
-
I tried LoRA tuning mpt-7b and mpt-7b-instruct. I can get summary like this:
wandb: Run summary:
wandb: eval/loss nan
wandb: eval/runtime 37.2157
wandb: …
-
看到你们展示的都是英文的交互界面,请问是否可以用中文来训练? 这里也有一个问题,如果基于LLaMa训练的话,中文instruct是否有效?期待回答。谢谢。
-
### Describe the feature
The following datasets were not found to be supported in the [readme ](https://github.com/hpcaitech/ColossalAI/tree/main/applications/ChatGPT/examples)for training the reward…
-
有场景需要对长文本通常有几万字进行信息抽取,qwen2的最大长度是32K,可以通过修改代码src/finetune.py中的参数max_source_length, max_target_length, cutoff_len: 最大输入、输出长度、截断长度支持长文本的输入和输出吗?
看到了 #7 的讨论由于训练模型的最大长度限制,因此可能无法很好处理, 想请教下Qwen2的所有Instruct模…
-
Study the LLM models trained on Spanish-language corpora, giving priority to those that have been built on the basis of:
- Llama-2
- Mistral
- Genmma
- Gpt-3.5
**Expected result:**
T…
-
I want to fine-tune LLaMa on data I got from a fandom wiki ([for example this page](https://minecraft.fandom.com/wiki/Iron_Ingot)) and was wondering how to design the json file with its "prompt", "inp…
-
The following error arises while training the model:
RuntimeError: Could not infer dtype of NoneType
The code is as follows:
!pip install ludwig
!pip install ludwig[llm]
import yaml
from…
-