Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,38 +1,50 @@
 {
-    "architectures": [
-        "LlamaForCausalLM"
-    ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bos_token_id": 128000,
-    "eos_token_id": 128009,
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 4096,
-    "initializer_range": 0.02,
-    "intermediate_size": 14336,
-    "max_position_embeddings": 131072,
-    "mlp_bias": false,
-    "model_type": "llama",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 32,
-    "num_key_value_heads": 8,
-    "pad_token_id": 128004,
-    "pretraining_tp": 1,
-    "rms_norm_eps": 1e-05,
-    "rope_scaling": {
-        "factor": 8.0,
-        "high_freq_factor": 4.0,
-        "low_freq_factor": 1.0,
-        "original_max_position_embeddings": 8192,
-        "rope_type": "llama3"
-    },
-    "rope_theta": 500000.0,
-    "tie_word_embeddings": false,
-    "torch_dtype": "float16",
-    "transformers_version": "4.52.4",
-    "unsloth_fixed": true,
-    "unsloth_version": "2025.6.5",
-    "use_cache": true,
-    "vocab_size": 128256
-}
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "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,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.55.0",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.8.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -10,5 +10,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.55.0"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc67a9227756ad96fc0d7bde3100f5f72e83c10bd2782933f1c78508b90d8f9b
+size 4652072853

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9a36ad418b0cd9b253f65771552d7dc05cf1abf1170b94de4b4d546aac255d
+size 1050673280