Upload model

config.json

@@ -17,6 +17,18 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "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"
+  },
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -32,7 +44,7 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.37.1",
   "use_cache": true,
   "vocab_size": 50257

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d00560d8910fbed77ffad4065dee5011c41ba401b1064e749c498ba9e20373
-size 497774208
+oid sha256:6bd061de3dc418812ea1bb6838aeee2fba1579b511ce2ccce5773549d0f5884c
+size 164295680