Trained with Unsloth

config.json

@@ -1,3 +1,29 @@
 {
-    "model_type": "llama"
-}
+  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "unsloth_version": "2024.5",
+  "use_cache": true,
+  "vocab_size": 128256
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8a4225f690e91acf3e741cc1098b0a4c078a7e3ac10d17994864fdb580db13
-size 4976698592
+oid sha256:e2e3b1cd97ebf9017c0335aa52751526a238b75b6e5fba1a8bb80f5ad2a7af53
+size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed5ce35e504612560025b83efab5a65814af42479e9bff33861ebb5c964406d
-size 4999802616
+oid sha256:024068ecfb5822c4fc488afb3deff0eb4219c801f51e5da8adb9021fc40a2dd3
+size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7cd75138ba90d61b3591ebc063d37a97199f073e784b876b8d4049d6135d93e
-size 4915916080
+oid sha256:c8efe5827b4fac280f6d146e8fd22885ea85c8fcfaddb4028743e105e4e49920
+size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357e8c388dc6170c8ae61ad5a5c105daf7867a099699ec0b86ad8a2baaf06966
+oid sha256:05e6779123f14aed58bd4a0e0b53c58449acdabf4aed2a049f11cbc89fd79d1e
 size 1168138808