初始化项目,由ModelHub XC社区提供模型

Model: AngelSlim/Qwen3-1_7b_fp8_static
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-05 01:07:13 +08:00
commit ef82ad9ff3
13 changed files with 1370 additions and 0 deletions

10
hf_quant_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"quantization": {
"quant_algo": "FP8",
"kv_cache_quant_algo": null,
"exclude_modules": [
"lm_head",
"model.embed_tokens"
]
}
}