vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

updated readme and colab

Browse source
This commit is contained in:
Concedo 2025-01-14 00:31:52 +08:00
parent e77d566268
commit 4d92b4e98e
2 changed files with 14 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -176,3 +176,4 @@ when you can't use the precompiled binary directly, we provide an automated buil
- Image Generation: [Anything v3](https://huggingface.co/admruul/anything-v3.0/resolve/main/Anything-V3.0-pruned-fp16.safetensors) or [Deliberate V2](https://huggingface.co/Yntec/Deliberate2/resolve/main/Deliberate_v2.safetensors) or [Dreamshaper SDXL](https://huggingface.co/Lykon/dreamshaper-xl-v2-turbo/resolve/main/DreamShaperXL_Turbo_v2_1.safetensors) - Image Generation: [Anything v3](https://huggingface.co/admruul/anything-v3.0/resolve/main/Anything-V3.0-pruned-fp16.safetensors) or [Deliberate V2](https://huggingface.co/Yntec/Deliberate2/resolve/main/Deliberate_v2.safetensors) or [Dreamshaper SDXL](https://huggingface.co/Lykon/dreamshaper-xl-v2-turbo/resolve/main/DreamShaperXL_Turbo_v2_1.safetensors)
- Image Recognition MMproj: [Pick the correct one for your model architecture here](https://huggingface.co/koboldcpp/mmproj/tree/main) - Image Recognition MMproj: [Pick the correct one for your model architecture here](https://huggingface.co/koboldcpp/mmproj/tree/main)
- Speech Recognition: [Whisper models for Speech-To-Text](https://huggingface.co/koboldcpp/whisper/tree/main) - Speech Recognition: [Whisper models for Speech-To-Text](https://huggingface.co/koboldcpp/whisper/tree/main)
- Text-To-Speech: [TTS models for Narration](https://huggingface.co/koboldcpp/tts/tree/main)

14
colab.ipynb
View file

@ -67,6 +67,11 @@
"LoadSpeechModel = False #@param {type:\"boolean\"}\n", "LoadSpeechModel = False #@param {type:\"boolean\"}\n",
"SpeechModel = \"https://huggingface.co/koboldcpp/whisper/resolve/main/whisper-base.en-q5_1.bin\" #@param [\"https://huggingface.co/koboldcpp/whisper/resolve/main/whisper-base.en-q5_1.bin\"]{allow-input: true}\n", "SpeechModel = \"https://huggingface.co/koboldcpp/whisper/resolve/main/whisper-base.en-q5_1.bin\" #@param [\"https://huggingface.co/koboldcpp/whisper/resolve/main/whisper-base.en-q5_1.bin\"]{allow-input: true}\n",
"WCommand = \"\"\n", "WCommand = \"\"\n",
"#@markdown <hr>\n",
"LoadTTSModel = False #@param {type:\"boolean\"}\n",
"TTSModel = \"https://huggingface.co/koboldcpp/tts/resolve/main/OuteTTS-0.2-500M-Q4_0.gguf\" #@param [\"https://huggingface.co/koboldcpp/tts/resolve/main/OuteTTS-0.2-500M-Q4_0.gguf\"]{allow-input: true}\n",
"WavTokModel = \"https://huggingface.co/koboldcpp/tts/resolve/main/WavTokenizer-Large-75-Q4_0.gguf\" #@param [\"https://huggingface.co/koboldcpp/tts/resolve/main/WavTokenizer-Large-75-Q4_0.gguf\"]{allow-input: true}\n",
"TTSCommand = \"\"\n",
"\n", "\n",
"import os\n", "import os\n",
"if not os.path.isfile(\"/opt/bin/nvidia-smi\"):\n", "if not os.path.isfile(\"/opt/bin/nvidia-smi\"):\n",
@ -85,6 +90,10 @@
" WCommand = \"--whispermodel wmodel.bin\"\n", " WCommand = \"--whispermodel wmodel.bin\"\n",
"else:\n", "else:\n",
" WCommand = \"\"\n", " WCommand = \"\"\n",
"if TTSModel and WavTokModel and LoadTTSModel:\n",
" TTSCommand = \"--ttsmodel ttsmodel.bin --ttswavtokenizer ttswavtok.bin --ttsgpu\"\n",
"else:\n",
" TTSCommand = \"\"\n",
"if FlashAttention:\n", "if FlashAttention:\n",
" FACommand = \"--flashattention\"\n", " FACommand = \"--flashattention\"\n",
"else:\n", "else:\n",
@ -110,7 +119,10 @@
" !aria2c -x 10 -o imodel.gguf --summary-interval=5 --download-result=default --allow-overwrite=true --file-allocation=none $ImgModel\n", " !aria2c -x 10 -o imodel.gguf --summary-interval=5 --download-result=default --allow-overwrite=true --file-allocation=none $ImgModel\n",
"if WCommand:\n", "if WCommand:\n",
" !aria2c -x 10 -o wmodel.bin --summary-interval=5 --download-result=default --allow-overwrite=true --file-allocation=none $SpeechModel\n", " !aria2c -x 10 -o wmodel.bin --summary-interval=5 --download-result=default --allow-overwrite=true --file-allocation=none $SpeechModel\n",
"!./koboldcpp_linux model.gguf --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize $ContextSize --websearch --quiet --remotetunnel $FACommand $MPCommand $VCommand $SCommand $WCommand\n" "if TTSCommand:\n",
" !aria2c -x 10 -o ttsmodel.bin --summary-interval=5 --download-result=default --allow-overwrite=true --file-allocation=none $TTSModel\n",
" !aria2c -x 10 -o ttswavtok.bin --summary-interval=5 --download-result=default --allow-overwrite=true --file-allocation=none $WavTokModel\n",
"!./koboldcpp_linux model.gguf --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize $ContextSize --websearch --quiet --remotetunnel $FACommand $MPCommand $VCommand $SCommand $WCommand $TTSCommand\n"
] ]
} }
], ],