Upload Qwen2ForCausalLM

config.json

@@ -16,11 +16,10 @@
   "num_hidden_layers": 64,
   "num_key_value_heads": 8,
   "quantization_config": {
-    "quant_method": "bitnet",
     "linear_class": "bitlinear",
+    "quant_method": "bitnet",
     "quantization_mode": "offline",
-    "with_rms_norm": true,
-    "pre_quantized": true
+    "with_rms_norm": true
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50fb4bf15397671bbc69567de4e68823c48c4a5a45f98a3126078e0de11c4f9
-size 3429862507
+oid sha256:74289be740e38e4f298a87b2e58d2280330fa3b0a073d491684a50a57b4f9e69
+size 4994256582

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fda9dedb4b8b708bb4396c1cabcafca2dc7ea9b7d41d7dfb0180731bf471ce8
-size 4568440619
+oid sha256:84482d6df92e2813ae2a2aba007c244937adc6a08d8b366c99b406f0ac784029
+size 4577611861