Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "unsloth/meta-llama-3.1-8b-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -7,6 +6,7 @@
   "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,
@@ -19,6 +19,18 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "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,
@@ -30,8 +42,9 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.44.2",
-  "unsloth_version": "2024.9.post4",
+  "transformers_version": "4.55.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.8.9",
   "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": "4.55.2"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da343a97c6436ce4250355e0ceb957d886d1cda857665294b098601673384942
+size 4913512899

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9f8fb3a26772f655e8508705dc914ca71e511cdb96ac35b11daa6958e64dc1
+size 1050673280