Nadav Timor

Same for me. Tried both with `pip` and `pip3`.

You might also find the `HfArgumentParser` relevant: https://github.com/huggingface/transformers/blob/514de24abfd4416aeba6a6455ad5920f57f3567d/src/transformers/hf_argparser.py#L109

> > You might also find the `HfArgumentParser` relevant: https://github.com/huggingface/transformers/blob/514de24abfd4416aeba6a6455ad5920f57f3567d/src/transformers/hf_argparser.py#L109 > > Not really if you have to install full HF package for it... The alternative below doesn't need the...

> What is the `max_seq_len` (or `max_position_embeddings`) of Mistral-7B-v0.1 when training? > > The official code says it is 128_000. (https://github.com/mistralai/mistral-src/blob/147c4e68279b90eb61b19bdea44e16f5539d5a5d/mistral/model.py#L201C69-L201C69) > > The config file in huggingface says it...

> I do not think we are going to be replacing the official OpenAI API call with yours. @StellaAthena, what are your thoughts on adding @ishaan-jaff's `litellm` alongside the official...

We recently [showed](https://arxiv.org/pdf/2405.04304) that even a relatively simple speculation lookahead controller can speed up the decoding. > Paradoxically, under conditions of high request rates or low speculation accuracy, latency may...

> This is intentional. From the relase notes: https://github.com/minimaxir/simpleaichat/releases/tag/v0.2.0 > > > In all cases, no messages are saved when using schema to prevent unintended behavior. You will have to...

> Maybe a parameter to also return the API response? Sounds legit.

I also need help with connecting to pods. Connecting via "Basic SSH Terminal" works, but "SSH over exposed TCP" doesn't. I checked the `~/.ssh/authorized_keys` file on the pod, and it...

> > In the comparison here, it seems that the performance of ngram is not yet higher than that of "no spec". Could you provide the specific startup parameters and...