najabba
/

4bit_quantized

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

najabba commited on Jun 9, 2025

Commit

8719f0e

·

verified ·

1 Parent(s): 8a9ca41

Upload Qwen3ForCausalLM

Files changed (2) hide show

config.json +3 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -20,10 +20,10 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float32",
     "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,

   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89da0c16dfc84bfdbcd61989f2d19308925425267f37266a8869fe790e8ec9e5
-size 559156248

 version https://git-lfs.github.com/spec/v1
+oid sha256:dd34634f97c4d10ece899563ab64913bb9471954922a5dcb9455e9a3befc1eca
+size 538883407