upload merged QLoRA model

config.json

@@ -21,21 +21,6 @@
   "num_key_value_heads": 16,
   "output_router_logits": false,
   "pad_token_id": 1,
-  "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,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d29e522315a6f90644e07c4dfe9cf2ffb752e1014762447b2a9ff253f75655
+oid sha256:f3d5eef8416498017681173f36dcfb1abe8c8d55976606b24d5ddc4cd3a4567b
 size 4997744872

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699049afc9d467e27aed0474919ad96d6bd9a471fdcc178186c74fc98dfe257d
+oid sha256:02d5302b7cbd28b4823eb75cf3c079540a82c33fe60be8715aecf6cb63a78e10
 size 4997235176

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c8360638dd0259cf700e4d965921091edddeb999342b03513e741a0858deea0
+oid sha256:fb6ee21428fc1d4c0b4ac92eebcab49066a115fdbc03533cc57874f9ebe6cef4
 size 3843741912