Commit History

  1. Added clarification between Qwen token count and word count

    Avishka
    Verified signature
    fc0882b
  2. Removed tildes to prevent markdown strikethrough rendering issues

    Avishka
    Verified signature
    ebab79e
  3. Clarified 550 Million token corpus size for CPT methodology verification

    Avishka
    Verified signature
    f073936
  4. Added explicit CPU execution instructions and code example

    Avishka
    Verified signature
    f97feb5
  5. Reverted to standard text completion code for Base/CPT model representation

    Avishka
    Verified signature
    31adec0
  6. Fixed code snippet to use apply_chat_template

    Avishka
    Verified signature
    643196c
  7. Cleaned up model description (removed Lankabizz and hardware specs)

    Avishka
    Verified signature
    a1c16d8
  8. Upload model.safetensors-00001-of-00002.safetensors

    Avishka
    Verified signature
    a345f95

  1. Upload model.safetensors-00002-of-00002.safetensors

    Avishka
    Verified signature
    bb1d0a3
  2. Upload tokenizer_config.json

    Avishka
    Verified signature
    7d78f28
  3. Upload tokenizer.json

    Avishka
    Verified signature
    fb2aeaf
  4. Upload processor_config.json

    Avishka
    Verified signature
    d8fe316
  5. Upload model.safetensors.index.json

    Avishka
    Verified signature
    baf01f4
  6. Upload config.json

    Avishka
    Verified signature
    d855312
  7. Upload chat_template.jinja

    Avishka
    Verified signature
    b7870d2
  8. Upload README.md

    Avishka
    Verified signature
    c629582
  9. initial commit

    Avishka
    Verified signature
    90696ab