Upload folder using huggingface_hub

config.json

@@ -19,6 +19,18 @@
   "num_key_value_heads": 32,
   "pad_token_id": 0,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "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,
   "rope_scaling": null,
   "rope_theta": 10000.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd346452c6531d9b69d5601670f6ba7ccadf354b121e4efe7400112ce396aa46
-size 2200119664
+oid sha256:50d21e3fbe40557946a5a8340b5a5cc4144af7376ea994db4d5a42a81c620c75
+size 3866058446