GGML
Datasets
All datasets matching “GGML”ciggml-vicuna-v0-quantizedThese are quantized ggml binary files for vicuna 7B and 13B models. The version of vicuna for these models are v0.
These files can be used in conjunction with minigpt4 ggml models 7B and 13B in minigpt4.cpp
Recommended are the Q5_K and Q6_K implementations. If there are any issues, use Q4_1 or Q4_0.
Vicuna Model Card
Model details
Model type:
Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
It is… See the full description on the dataset page: https://huggingface.co/datasets/maknee/ggml-vicuna-v0-quantized.ggml-japanese-gpt2Windowsの方はggml-japanese-gpt2の実行ファイルで動くと思います。
同じファイル名のggml形式のbinとSentencePiece形式のmodelをダウンロードして保存してください。
使い方は以下のようになります。
gpt-2.exe -m ggml-model-japanese-gpt2-medium-f16.bin -p "こんにちは"
ggml-model-japanese-gpt2-xsmallのファイル形式がおかしくなっているので、ダウンロードしても動きません。
あとで修正します。
minigpt4-13b-ggmlThese are quantized ggml binary files for minigpt4 13B model.
These files can be used in conjunction with vicuna v0 ggml models to get minigpt4 working.
Not all implementations were tested. If there are any issues, use f16.
minigpt4-7b-ggmlThese are quantized ggml binary files for minigpt4 7B model.
These files can be used in conjunction with vicuna v0 ggml models to get minigpt4 working.
Not all implementations were tested. If there are any issues, use f16.
LaMini-LM-dataset-TheBloke-h2ogpt-falcon-40b-v2-GGML-eval-llama2
Dataset Card for "LaMini-LM-dataset-TheBloke-h2ogpt-falcon-40b-v2-GGML"
More Information needed