-
Need to step up to larger models with permissive license. 30b Llama works, but can't be used. 6b is too small, bad results. So next better choice is gpt-neox-20b.
this works:
`CUDA_VISIBLE_DEVICES…
-
**Describe the bug**
It generate the error when running the generate program
**To Reproduce**
Steps to reproduce the behavior:
1. run "./deepy.py generate.py ./configs/20B.yml -i prompt.txt -o sam…
-
I'm running this sample code [https://github.com/aws-neuron/transformers-neuronx#hugging-face-generate-api-support] using GPT-NeoX on an inf2.24xlarge instance, but the model.generate method kills the…
-
Hello! Thanks for your great work, but I met some problems when trying to replicate the results.
Specifically, I cannot find convert_raw_llama_weights_to_hf.py as depicted in [README.md](https://gi…
-
Hi, I am able to reproduce building and running the model locally via TensorRT-LLM.
I build using:
```
python3 build.py --model_dir /finetune-gpt-neox/models--meta-llama--Llama-2-7b-hf/snapsho…
-
Before loading omnitrace:
```
(gpt-neox-rocm5.6.0) langx@frontier07915:/lustre/orion/csc549/scratch/langx> python
Python 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0] on linux
Type "help", "c…
R0n12 updated
5 months ago
-
https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft
-
```bash
# dataset/download_books.sh
wget https://the-eye.eu/public/AI/pile_neox/data/BookCorpusDataset_text_document.bin
wget https://the-eye.eu/public/AI/pile_neox/data/BookCorpusDataset_text_docu…
-
### Feature request
I encountered a KeyError while loading the phi3-v vision model into Optimum Huggingface. The error message states:
```
KeyError: 'phi3-v model type is not supported yet in Nor…
-
Hi, dear:
Thank you very much for your open source. Will the code of FIM dataset construction and training be made public? such as the number of lines or length of the code for Prefix, suffix, and…