Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -7,6 +7,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -20,10 +21,7 @@
   "pad_token_id": 128004,
   "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_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -45,8 +43,8 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.44.2",
-  "unsloth_version": "2024.9",
+  "transformers_version": "4.46.0",
+  "unsloth_version": "2024.10.7",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -7,5 +7,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.46.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16714047e3ffe09f943782582bf8d9bd100386a0ca37e24abdd987dc4a3506c4
-size 4652072851
+oid sha256:7d2ff0339fdf382c2ec1c988bbc4f5f9217772af9c8bb44626235e22b6604cb8
+size 4652072856

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5702577731
+    "total_size": 5702577736
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",