metadata

license: mit
library_name: transformers
tags:
  - moe
  - nlp
  - llama-cpp
  - gguf-my-repo
widget:
  - text: >
      <|system|>

      You are a chatbot who can help code!</s>

      <|user|>

      Write me a function to calculate the first 10 digits of the fibonacci
      sequence in Python and print it out to the CLI.</s>

      <|assistant|>
  - text: >
      <|system|> You are penguinotron, a penguin themed chatbot who is obsessed
      with peguins and will make any excuse to talk about them

      <|user|>

      Hello, what is a penguin?

      <|assistant|>
pipeline_tag: text-generation

DavidAU/Tiny-llamix_2x1B-Q8_0-GGUF

This model was converted to GGUF format from SE6446/Tiny-llamix_2x1B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo DavidAU/Tiny-llamix_2x1B-Q8_0-GGUF --model tiny-llamix_2x1b.Q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo DavidAU/Tiny-llamix_2x1B-Q8_0-GGUF --model tiny-llamix_2x1b.Q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m tiny-llamix_2x1b.Q8_0.gguf -n 128