vmajor

Finetuning example?

4

I see good amount of focus on understanding how to perform full training of Mamba, but what about PEFT? Adapters/LoRA finetuning. The base models are in fact "Ready" for a...

Question: what format do the models need to be in for merging?

14

I must have missed something, but for the life of me I cannot find any information about the format of the models that mergekit expects. Are they pytorch, safetensors? Can...

{ "message" : "Required part file is missing", "code" : 34 }

7

**Describe the bug** When attempting to make a curl request in terminal I get the following response: ``` { "message" : "Required part file is missing", "code" : 34 }...

Instructions?

2

I am entirely new to pio and the architecture of the artificial-nose changed from straight up Arduino to PIO since the introduction was written. Specifically, there are no instructions on...

I am having trouble locating your training dataset. I am assuming it is CASIA, but it cannot be downloaded from anywhere that I could find it. The dataset that I...

It does not work. Either take it down or fix it.

11

Has many errors. URL is incorrect for fetch, ingest.py gives an error even when the URL is changed to something that works and enough content is fetched. Too much effort...

AssertionError: Model can't be found.

1

Trying to run babyagi with `docker-compose up` results in `AssertionError: Model can't be found.` Model path is correct in the host file system. It makes me think that the dockerised...

Support Microsoft Guidance

16

I am trying to use a 'custom tokenizer' but I am unable to see how can I invoke it. Also can we use a standard tokenizer from HF by pulling...

Here is one error that leaves a trace. The script also sometimes exists silently without any error message. Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py", line 672, in urlopen chunked=chunked,...