Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -12,13 +12,14 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "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,
@@ -33,9 +34,9 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
   "unsloth_version": "2024.5",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.41.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b2a77b09e92bdff3854850b17a452b4d17863c400d0ed8b17270d8b6654a85
-size 4652072863
+oid sha256:ef209c052b3997d771cdc70ca185fde83f4b011b93dd3cb4730b6199e01736ae
+size 4652072928

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b53fa307a8988f692ffbfdb1fc2503ae0980a799e3fc9b75f1d5e23781fb37
+oid sha256:7c5394fe848f6eafef2a44f085e7b72e5ef0d315f98aa87b3827c2b1e6983b89
 size 1050673280

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5702577743
+    "total_size": 5702577744
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",