[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support Mixtral #365

Open
WebCloud opened this issue Apr 10, 2024 · 4 comments
Open

Support Mixtral #365

WebCloud opened this issue Apr 10, 2024 · 4 comments

Comments

@WebCloud
Copy link

It seems that bumblebee is not capable of loading Mixtral-8x7B models (base or instruct). I've checked the files and it should be able to load the model (in theory) since it is capable of loading Mistral-7b files, but I keep getting

** (ArgumentError) could not match the class name "MixtralForCausalLM" to any of the supported models, please specify the :module and :architecture options
    (bumblebee 0.5.3) lib/bumblebee.ex:409: Bumblebee.do_load_spec/4
    (bumblebee 0.5.3) lib/bumblebee.ex:578: Bumblebee.maybe_load_model_spec/3
    (bumblebee 0.5.3) lib/bumblebee.ex:566: Bumblebee.load_model/2
    #cell:4lsfbdujnkoinq5p:3: (file)

Both configuration files have the same reference to MixtralForCausalLM and Mixtral-8x7B has the safetensors filers.

Mix.install(
  [
    {:bumblebee, "~> 0.5.3"},
    {:exla, ">= 0.0.0"}
  ],
  config: [nx: [default_backend: EXLA.Backend]]
)

repo = {:hf, "mistralai/Mixtral-8x7B-Instruct-v0.1"}

{:ok, model_info} = Bumblebee.load_model(repo, type: :bf16, backend: EXLA.Backend) # errors
{:ok, tokenizer} = Bumblebee.load_tokenizer(repo)
{:ok, generation_config} = Bumblebee.load_generation_config(repo)
@jonatanklosko jonatanklosko changed the title Error whist trying to load hf mistralai/Mixtral-8x7B-Instruct-v0.1 Support Mixtral Apr 10, 2024
@jonatanklosko
Copy link
Member

@WebCloud Bumblebee needs implementation for each model type in order to load it. Mixtral is not implemented currently, while Mistral is.

@WebCloud
Copy link
Author

I see! Well, I am quite fresh on Elixir, but I'd be happy to help however I can.

@jonatanklosko
Copy link
Member

For an example of adding a model you can see Mistral #264. The corresponding hf/transformers code is modeling_mixtral.py.

However, note that Nx/EXLA doesn't support quantization yet, and the bf16 model is around 100GB, so it is not very practical for running on the GPU at this point.

@WebCloud
Copy link
Author

Cool! thanks for the resources!

@hwuethrich hwuethrich mentioned this issue May 2, 2024
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@WebCloud @jonatanklosko