Mistral-Small-24B-Instruct-MNN / export_args.json
darkmaniac7's picture
Add MNN Q4 conversion for TokForge mobile inference
bf29b79 verified
{
"path": "/root/models/hf_convert_queue/Mistral-Small-24B-Instruct",
"type": null,
"tokenizer_path": "/root/models/hf_convert_queue/Mistral-Small-24B-Instruct",
"eagle_path": null,
"lora_path": null,
"gptq_path": null,
"dst_path": "/root/models/hf_uploads/Mistral-Small-24B-Instruct-MNN",
"verbose": false,
"test": null,
"export": "mnn",
"onnx_slim": false,
"quant_bit": 4,
"quant_block": 128,
"visual_quant_bit": null,
"visual_quant_block": null,
"lm_quant_bit": 4,
"lm_quant_block": 128,
"mnnconvert": "../../../build/MNNConvert",
"ppl": false,
"awq": false,
"hqq": false,
"omni": false,
"transformer_fuse": false,
"group_conv_native": false,
"smooth": false,
"sym": false,
"visual_sym": false,
"seperate_embed": true,
"lora_split": false,
"calib_data": null,
"act_bit": 16,
"embed_bit": 16,
"act_sym": false,
"quant_config": null,
"generate_for_npu": false,
"skip_weight": false,
"omni_epochs": 20,
"omni_lr": 0.005,
"omni_wd": 0.0001,
"tie_word_embeddings": false
}