From 94fa47a868fb9d7b43334c5de72abb359ddd9606 Mon Sep 17 00:00:00 2001 From: Caio Oliveira Date: Fri, 18 Oct 2024 03:10:01 -0300 Subject: [PATCH] Update Mistral LLMs notebook (#402) --- notebooks/llms.livemd | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/notebooks/llms.livemd b/notebooks/llms.livemd index bf2474ce..389a4754 100644 --- a/notebooks/llms.livemd +++ b/notebooks/llms.livemd @@ -90,8 +90,11 @@ Nx.Serving.batched_run(Llama, prompt) |> Enum.each(&IO.write/1) We can easily test other LLMs, we just need to change the repository and possibly adjust the prompt template. In this example we run the [Mistral](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) model. +Just like Llama, Mistral now also requires users to request access to their models, so make sure you are granted access to the model, then generate a [HuggingFace auth token](https://huggingface.co/settings/tokens) and put it in a `HF_TOKEN` Livebook secret. + ```elixir -repo = {:hf, "mistralai/Mistral-7B-Instruct-v0.2"} +hf_token = System.fetch_env!('LB_HF_TOKEN') +repo = {:hf, "mistralai/Mistral-7B-Instruct-v0.2", auth_token: hf_token} {:ok, model_info} = Bumblebee.load_model(repo, type: :bf16, backend: EXLA.Backend) {:ok, tokenizer} = Bumblebee.load_tokenizer(repo) @@ -109,7 +112,7 @@ generation_config = serving = Bumblebee.Text.generation(model_info, tokenizer, generation_config, - compile: [batch_size: 1, sequence_length: 1028], + compile: [batch_size: 1, sequence_length: 512], stream: true, defn_options: [compiler: EXLA] )