(Trained with Unsloth)

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -57,7 +57,7 @@
   "num_key_value_heads": 8,
   "pad_token_id": 151654,
   "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d98c9ae6e07097bfa49fca81ca20fd4c2439c989143417e16c2a0f6cb3d77f77
-size 4828897876
+oid sha256:db9d80bfd08559eba0880ce54921f8e7cb82730a8d23695507991dd7d8587820
+size 4828898032

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c3a004b23371ef2cf248a2baf4869d3969dbcf37e792b48008d73036872855
+oid sha256:20c2d6366ab85c90786ccdd829cd2b9e7d30ef3b2ebbb998280e7e4014b542ff
 size 1244659840

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
     "total_parameters": 8190735360,
-    "total_size": 6073360284
+    "total_size": 6073360296
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",