Trained with Unsloth

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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,
+  "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": "4.48.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.1.8",
+  "use_cache": true,
+  "vocab_size": 128256
+}

pytorch_model-00001-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289b284ab8a340994c600b0197d4ffcc69177ec6c968f01951ef8fb1c0b76428
+oid sha256:87395f8973987d177bddd23a503bef447d21df1fc8ccb851bb624782e667bd24
 size 4976718466

pytorch_model-00002-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6eba82e200e4494b1a7a36db2d6e31e48b17d01d3d12127e46a11eb6c290bf
-size 4999827270
+oid sha256:65bb5311a905ebae68909ac6cc0340c7e7334b7c7d4463152f3eaa6841f44316
+size 4999827334

pytorch_model-00003-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3d482243546e16c32492a6762d2b72b8756116eeb18efb9386244f8846676c
+oid sha256:16075896c592e55e80d0c27930275018f7b49eb76ad305b59834f3c02da4d676
 size 4915939082

pytorch_model-00004-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8965db13cd4586c87ddd53b46c846996972963f1994659c52e03941a4130bff
+oid sha256:c9519e0c068221116599ef0fdc15151690e7dbf38f4f432103caabd765c7bb98
 size 1168140873