Aaron Miller

I'm seeing a similar issue, with a failure of `virtio_net: Could not create vmnet interface, permission denied or no entitlement? (status = 1001)` when trying to run any xhyve variant...

At least on my end, the issue I and @therealprof are having seems to have been caused by NAT/Network Sharing having been disabled on my mac. `com.apple.NetworkSharing` must be running...

You need to clone the submodules. Run `git submodule update --init`

you probably *don't* want to use madvise+`MADV_SEQUENTIAL`, as in addition to increasing the amount of readahead it also causes pages to be evicted after they've been read - the entire...

the `mmap` operation itself is going to have its own portability issues, supporting all platforms on a first pass with no `#ifdef`s is unlikely here - `mmap` also requires the...

The discrepancy here is because Falcon's tokenizer.json specifies a different pre_tokenizer. Most BPE-using models use the config that mimics GPT2 - i.e. "pretokenizing" is done with the [standard regex](https://github.com/karpathy/minGPT/blob/master/mingpt/bpe.py#L92): ```json...

trying to test locally on top of main - doesn't rebase on main cleanly

sorry, the build errors aren't windows specific, `main` still seems to have gotten away from this again - there are conflicts (that didn't become actual merge conflicts) with the `prompt()`...

Tried to convert and run the model locally with the included script, getting a failure to load - is the conversion script out of sync? ``` replit_model_load: loading model from...

> Hmm just ran conversion script again and is working fine for me. Which OS are you working on? MacOS, I checked out your branch and ran ```bash python ./gpt4all-backend/scripts/convert_replit_hf_to_ggml.py...