Xenova/llama2.c-stories42M
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Xenova/llama2.c-stories42M
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-24 18:51:51 +08:00
commit 9440ccece0
43 changed files with 93773 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

107
quantize_config.json Normal file
View File

@@ -0,0 +1,107 @@
{
"per_channel": false,
"reduce_range": false,
"per_model_config": {
"decoder_with_past_model": {
"op_types": [
"Unsqueeze",
"Transpose",
"Neg",
"Softmax",
"If",
"Identity",
"Expand",
"Where",
"Constant",
"Mul",
"Shape",
"Sigmoid",
"MatMul",
"Div",
"Squeeze",
"Range",
"Sub",
"Pow",
"Gather",
"Concat",
"ReduceMean",
"ConstantOfShape",
"Reshape",
"Sqrt",
"Cast",
"Slice",
"Add",
"Equal"
],
"weight_type": "QInt8"
},
"decoder_model": {
"op_types": [
"Unsqueeze",
"Transpose",
"Neg",
"Less",
"If",
"Softmax",
"Identity",
"Expand",
"Where",
"Constant",
"Mul",
"Shape",
"Sigmoid",
"MatMul",
"Div",
"Squeeze",
"Range",
"Sub",
"Pow",
"Gather",
"Concat",
"ReduceMean",
"ConstantOfShape",
"Reshape",
"Slice",
"Cast",
"Sqrt",
"Add",
"Equal"
],
"weight_type": "QInt8"
},
"decoder_model_merged": {
"op_types": [
"Unsqueeze",
"Transpose",
"Neg",
"Less",
"If",
"Softmax",
"Identity",
"Expand",
"Where",
"Constant",
"Mul",
"Shape",
"Sigmoid",
"MatMul",
"Div",
"Squeeze",
"Range",
"Sub",
"Pow",
"Gather",
"Concat",
"ReduceMean",
"ConstantOfShape",
"Reshape",
"Slice",
"Cast",
"Sqrt",
"Add",
"Equal"
],
"weight_type": "QInt8"
}
}
}