Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "unsloth/llama-3.1-8b-instruct-unsloth-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -20,6 +19,18 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,
@@ -31,7 +42,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.50.0.dev0",
   "unsloth_fixed": true,
   "unsloth_version": "2025.3.17",
   "use_cache": true,

generation_config.json

@@ -10,5 +10,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.49.0"
+  "transformers_version": "4.50.0.dev0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b15a4b0bc7157bfadc78bb86dcaf9116f3ebcae6d819ac947017e595210a6522
-size 4652073135
+oid sha256:e11b472f17ce6924d78e81d10c80950f3da2b3a482abacbeb221f206662fabef
+size 4652073141