初始化项目，由ModelHub XC社区提供模型

Model: groxaxo/octen-embedding-8b-w4a16 Source: Original Platform
2026-08-21 08:35:12 +08:00
commit 80d1d43641
13 changed files with 1248 additions and 0 deletions
--- a/quantization_config.json
+++ b/quantization_config.json
@@ -0,0 +1,15 @@
+{
+  "bits": 4,
+  "data_type": "int",
+  "group_size": 128,
+  "sym": true,
+  "amp": false,
+  "batch_size": 1,
+  "gradient_accumulate_steps": 8,
+  "low_gpu_mem_usage": true,
+  "nsamples": 8,
+  "seqlen": 512,
+  "autoround_version": "0.12.2",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq"
+}