-
### System Info
transformers v4.30.0
python 3.8
Training using `deepspeed stage zero 2` hit an error when in evaluation/prediction loop. Both prediction/evaluation initiate [deepspeed with infere…
-
Hi I use the commands in the README to run this project.
As you don't specify the model repo, I download model from here: https://huggingface.co/daryl149/llama-2-7b-chat-hf
The build process is…
-
## ❓ General Questions
Every time I try to paste the repo link https://huggingface.co/mlc-ai/mlc-chat-vicuna-v1-7b-q3f16_0 the app tells me „Add model failed.
Can anyone help?
-
Thanks for your great work on this project! As mentioned in #25 The script `scripts/github-prepare-download.sh` which is referenced in [this README.md](https://github.com/togethercomputer/RedPajama-Da…
-
## 🐛 Bug
Hello.
I try to build model but my gpu is not work and i get error.
$ python build.py --hf-path=databricks/dolly-v2-3b --quantization q4f16_0 --target android --max-seq-len 768
Weight…
-
## 🐛 Bug
Previously, I was able to build the app from source and then it would crash upon initializing the chat with the downloaded weights.
Now with the [latest changes](https://github.com/mlc-…
-
PR497 https://github.com/EleutherAI/lm-evaluation-harness/pull/497 breaks the evaluation of MMLU, it would be great if this commit could be reverted.
There are 3 major leaderboard for LLM evalution…
-
## 🐛 Bug
```
❯ python build.py --hf=eachadea/vicuna-7b-1.1 --target cuda
Weights exist at dist/models/vicuna-7b-1.1, skipping download.
Using path "dist/models/vicuna-7b-1.1" for model "vicuna-7b-…
-
(gh_mlc-llm) amd00@asus00:~/llm_dev/mlc-llm$ ll build
total 122328
drwxrwxr-x 5 amd00 amd00 4096 6月 12 22:31 ./
drwxrwxr-x 19 amd00 amd00 4096 6月 12 22:12 ../
-rw-rw-r-- 1 amd00 amd0…
-
First of all: thank you very much for your contribution!
That said, I still have a question: in order to really "democratise" AI, a trained model will be needed that may be used for (fine-tuning an…