Upload LlamaForCausalLM

config.json

@@ -17,6 +17,21 @@
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
   "pretraining_tp": 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.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71a84565417bd74bd7341ac6bb014a30167071337f0636e163580d10560bc1e
-size 4400216536
+oid sha256:e232d9a4dc5e260d5a830fbfc3bbbb5ce31a19b2a7a6c89ad5699fc549c39eb1
+size 1024784727