Nayantheboss
/

MNLP_M2_quantized_model

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

Nayantheboss commited on Jun 11

Commit

326e243

·

verified ·

1 Parent(s): 930c7c4

Upload Qwen3ForCausalLM

Files changed (2) hide show

config.json +7 -7
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -18,18 +18,18 @@
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
     "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,
     "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",
+    "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,
+    "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 sha256:7b27f90bdd0e0146c58e0c8b8756c5895a63e98e520bb2768cf228a2068a5da5
-size 538883110

 version https://git-lfs.github.com/spec/v1
+oid sha256:70dbf9bb094981e0a2bd5916ffea11ede729381f00aa6dc518b7dd8a118125af
+size 753150052