clejordan
/

MNLP_M3_bnbquantized_final

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

clejordan commited on Jun 10, 2025

Commit

12da260

·

verified ·

1 Parent(s): f1e922f

Upload Qwen3ForCausalLM

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -24,7 +24,7 @@
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
     "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": true,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,

     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
     "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,