Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -6,6 +6,7 @@ tags:
 - unsloth
 - qwen2
 - trl
+- sft
 license: apache-2.0
 language:
 - en

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Theros/Qwen2.5-ColdBrew-R1",
+  "_name_or_path": "Theros/Qwen2.5-ColdBrew-Aetheria",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -19,7 +19,7 @@
   "organization": "SvalTek",
   "pad_token_id": 151665,
   "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,
@@ -35,9 +35,9 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.48.3",
-  "unsloth_version": "2025.2.12",
+  "unsloth_version": "2025.3.8",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:208058b7019c8f8deb04a6ab2b9ab12c00a6e31c495252db78a5f23649dcef58
-size 4454406572
+oid sha256:b5bdde34d9daa88ebd3c39449a3f9b9537eaf1cb83c5ba7e629b146ffebf2f22
+size 4454406713

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95743370c3723fa309168b59c6852396ec0495b5c1bf5affb089afd2fc915d2f
+oid sha256:ecfd97e2984dad183f6e057aa379f9d8d00dda2f2b305fa7fe7b5183ef1fdfba
 size 1087142016

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5541392172
+    "total_size": 5541392169
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",