Hugging Face's logo

Spaces:
Voided0ne
/
DeCoder
Sleeping

App Files Community
DeCoder / app.py

Commit History

  1. Fix llama release archive filename

    identityvoid
    497d9a2

  2. Fix llama release download URL

    identityvoid
    2a605cf

  3. Fix llama.cpp CUDA runtime loading

    identityvoid
    b48f0ec

  1. Disable Gradio SSR for Space compatibility

    identityvoid
    0b060ae

  2. Convert model app to Gradio ZeroGPU

    identityvoid
    3fd1be3

  1. Update removal of append_history=False

    ffreemt
    7564484

  1. Update Waking-up-takes-about-9min-Sleep-after-15min-of-inactivity

    ffreemt
    1d516ba

  1. Update overwrite libbitsandbytes_cpu.so with libbitsandbytes_cuda118.so lsb_release -a bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    7e9b0c1

  2. Update overwrite libbitsandbytes_cpu.so with libbitsandbytes_cuda118.so lsb_release -a bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    08612a4

  3. Update overwrite libbitsandbytes_cpu.so with libbitsandbytes_cuda118.so lsb_release -a bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    fae4857

  4. Update lsb_release -a bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    dec88ff

  5. Update lsb_release -a bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    297f7a4

  6. Update lsb_release -a bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    f8bc02a

  7. Update lsb_release -a bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    ca48eff

  8. Update lsb_release -a bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    3895ca8

  9. Update bitsandbytes device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    b55d7c2

  1. Update device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    f924882

  2. Update device_map={'': 0} rich, check nvidia-smi with subproces.run

    ffreemt
    b0c90a1

  3. Update check nvidia-smi with subproces.run

    ffreemt
    60d0767

  1. Back to Qwen/Qwen-7B-Chat

    ffreemt
    56ad8d6

  1. Update tangger/Qwen-7B-Chat since Qwen/Qwen-7B-Chat is gone

    ffreemt
    5f4757d

  1. Update

    ffreemt
    e8c556f

  2. Update

    ffreemt
    6afaebf

  3. Update

    ffreemt
    187485d

  4. Update

    ffreemt
    ad51515

  5. Update pundkey='#' {poundkey} in info

    ffreemt
    66acbac

  6. Update API ready, TODO: fix info

    ffreemt
    c48ba74

  1. Update logger.trace disabled

    ffreemt
    584239a

  1. Update yield from bot_stream in bot_stream_state

    ffreemt
    b00e246

  2. ffreemt
    2987cd6

  3. Update turn trace on

    ffreemt
    79b022b

  4. Update info on top_k=0

    ffreemt
    7ea83b4

  5. Update user_clear for submit.click buttn

    ffreemt
    d84480c

  6. Update model.generation_config.update

    ffreemt
    f5c4b5c

  7. Update single model

    ffreemt
    558796e

  8. Update model replaced by stats.value.llm

    ffreemt
    efc09da

  9. ffreemt
    41e9e77

  10. ffreemt
    d017960

  11. Update

    ffreemt
    4bef18d

  1. ffreemt
    103cf8f

  2. ncc

    ffreemt
    7725b42

  3. Update

    ffreemt
    a27c4fb