najabba
/

MNLP_M2_quantized_model

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

najabba commited on May 30, 2025

Commit

accfa12

·

verified ·

1 Parent(s): 5d0c3eb

Upload Qwen3ForCausalLM

Files changed (2) hide show

config.json +4 -4
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -18,8 +18,8 @@
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "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",
@@ -28,8 +28,8 @@
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,

   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
     "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,

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 sha256:3e999ff30129129ca7e4f992952d8d54136b2d0a820faae36546de60920cfa6f
+size 753150172