Gary Mulder

Chopin and Ragtime model training and output with loss of 0.0049

1

@Skuldur thanks for a great musical project! I pulled down some MIDI files from [Kunstderfuge](http://kunstderfuge.com) and switched your code to use CUDA and Batch Normalisation to get a loss of...

Wandb - Selected runs are not logging media for the key objective/*, but instead are logging values of type list.

2

 Getting this error in wandb when running either: ``` ./examples/sentiment/scripts/gpt2-sentiment.py ./examples/sentiment/scripts/t5-sentiment.py ``` It looks like the data are lists of tensors. From the TRL Showcase it should be displaying...

Increasing PPOconfig training steps does not increase the number of training iterations

2

Apologies in advance if I'm missing something obvious, but when I increase `PPOconfig.steps` from the default of 20000 PPO doesn't seem to train for more iterations using accelerate with 4...

Document check sums of models so that we can confirm issues are not caused by bad downloads or conversion

9

Can someone please confirm the following md5 sums are correct? I regenerated them with the latest code. ``` $ md5sum ./models/*/*.pth | sort -k 2,2 0804c42ca65584f50234a86d71e6916a ./models/13B/consolidated.00.pth 016017be6040da87604f77703b92f2bc ./models/13B/consolidated.01.pth f856e9d99c30855d6ead4d00cc3a5573...

Create issue template for bug and enhancement issues

1

The following is a proposed template for creating new issues. If people think the tone could be improved, I'd appreciate feedback! ___ # Prerequisites Please answer the following questions for...

No output after commit 84d9015 on Android

4

### Discussed in https://github.com/ggerganov/llama.cpp/discussions/234 Originally posted by **ShouNichi** March 17, 2023 When `git checkout 84d9015` and `make`, there will be no output (only the model loading message) in termux. `git...

sha256 check sums to verify original and converted model data

5

Not a developer, so my git-fu is a bit rusty. Hopefully this pull request covers everything?!? * Add shadow `./model.sha256` dir containing a dir for each model and a corresponding...

Issue template proposal

2

I wrote the original issue template for llama.cpp. Happy to help manage the issues a bit here, but can we have something similar, pls? --- # Prerequisites Please answer the...

LORA fine-tuning with openlm-research/open_llama_7b as a plugin replacement for decapoda-research/llama-7b-hf

23

Hi. Thanks for the open sourced models! This is a major step forward to the democratization of LLMs. I'm trying to fine tune `openlm-research/open_llama_7b` using the LORA. I first tried...

[Dockerfile: ](https://github.com/genepi/cloudgene/blob/master/Dockerfile) `FROM genepi/cdh5-hadoop-mrv1:latest` [[[cdh5-hadoop-mrv1](https://github.com/genepi/cdh5-hadoop-mrv1/tree/master)](https://github.com/genepi/cdh5-hadoop-mrv1/blob/master/Dockerfile):](https://github.com/genepi/cdh5-hadoop-mrv1/blob/master/Dockerfile) `FROM ubuntu:14.04` It looks like Cloudera has dropped access to later versions of CDH: ``` As of February 1, 2021, all downloads of CDH and...