metadata

language:
  - en
license: apache-2.0
tags:
  - chemistry
  - biology
  - not-for-all-audiences
  - merge
  - code
  - llama-cpp
  - gguf-my-repo
base_model: Locutusque/TinyMistral-248M-v2.5
datasets:
  - Locutusque/hercules-v1.0
  - Open-Orca/SlimOrca-Dedup
inference:
  parameters:
    do_sample: true
    renormalize_logits: false
    temperature: 0.8
    top_p: 0.14
    top_k: 12
    min_new_tokens: 2
    max_new_tokens: 96
    repetition_penalty: 1.15
    no_repeat_ngram_size: 5
    epsilon_cutoff: 0.002
widget:
  - text: |
      <|im_start|>user
      Write me a Python program that calculates the factorial of n. <|im_end|>
      <|im_start|>assistant

BasedBots/TinyMistral-248M-v2.5-Instruct-Q4_K_M-GGUF

This model was converted to GGUF format from Locutusque/TinyMistral-248M-v2.5-Instruct 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 BasedBots/TinyMistral-248M-v2.5-Instruct-Q4_K_M-GGUF --model tinymistral-248m-v2.5-instruct.Q4_K_M.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo BasedBots/TinyMistral-248M-v2.5-Instruct-Q4_K_M-GGUF --model tinymistral-248m-v2.5-instruct.Q4_K_M.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 tinymistral-248m-v2.5-instruct.Q4_K_M.gguf -n 128