SekoiaTree
/

MNLP_quantized_model_scratch

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions

SekoiaTree commited on 11 days ago

Commit

a00832f

·

verified ·

1 Parent(s): fc35f27

Upload Qwen3ForCausalLM

Files changed (2) hide show

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

config.json CHANGED Viewed

@@ -48,8 +48,8 @@
   "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",
@@ -58,8 +58,8 @@
     "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 sha256:29c472906a077e3bdfc9d392b4ec01b26b699ce093559c330e727d469e972354
-size 559155940

 version https://git-lfs.github.com/spec/v1
+oid sha256:30df4133101af2c245680289f4f1d5cf7d2ed5a6e817af40e8fbd90cb0454426
+size 753150052