Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -18,7 +18,7 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "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,
@@ -33,7 +33,7 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
   "unsloth_version": "2024.4",
   "use_cache": true,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3e2fff3576c64acf996583a43bc5cefffb977cc2bda189b40b4117b120d9bef
-size 4652072867
+oid sha256:ed8dafd1e3ecabbec909d807581eb3030a61086f0efaf2d30295a9f0f5540283
+size 4652072923

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
+oid sha256:7c5394fe848f6eafef2a44f085e7b72e5ef0d315f98aa87b3827c2b1e6983b89
 size 1050673280

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5702577747
+    "total_size": 5702577739
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",