Upload LlamaForCausalLM

config.json

@@ -25,8 +25,8 @@
   "pad_token_id": 128004,
   "pretraining_tp": 1,
   "quantization_config": {
-    "_load_in_4bit": false,
-    "_load_in_8bit": true,
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
@@ -35,8 +35,8 @@
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef5b8650b4aafbcfd70b6adc35da16a689d7e1117d51b2ec4028b7ccc5867db8
-size 1500097816
+oid sha256:c4c8de245510d5c99f62be6ada94d69c319f6aa8d5fc83b05fbd4b45ad60f38a
+size 1072901744