(Trained with Unsloth)

config.json

@@ -1,3 +1,30 @@
 {
-    "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,
+  "mlp_bias": false,
+  "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": "float16",
+  "transformers_version": "4.41.1",
+  "unsloth_version": "2024.5",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.41.0"
+  "transformers_version": "4.41.1"
 }

pytorch_model-00001-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7142f59b1a286a2d767ba1f9d6a24d16be45ca3795a6d0ce0cfc81af1a2c8e
+oid sha256:616f35e4cc92ab9d1aa0ef6078caf72bd1f4be3d8598bbecf127b0452e340b7e
 size 4976718466

pytorch_model-00002-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9503ce83dd49512428178eee53ddd0e29edadf921bf3c751436edd677547d9a2
+oid sha256:cd3ed38a898f041626ee2450a5faa095b3126fcfee79a78e9c0d3ff6b4712a81
 size 4999827206

pytorch_model-00003-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fc325e0def8a4a1c24b6f6f8b0bf3b14983051600a29205042f5f8c4b41bfb
+oid sha256:0f9b92cce5d1c306c3467da7ba73cc7e236929cd2d7833fe24ab2ae64b457c37
 size 4915939082

pytorch_model-00004-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519f7028a16595bf02bf50aa2abf695f539b78a21134108797f066ea5a6866aa
+oid sha256:a669e1e54267939ccd443f0ec87ee17393e5021cf8af7e0820a0ca1513d52630
 size 1168140873

tokenizer_config.json

@@ -2067,6 +2067,6 @@
   ],
   "model_max_length": 8192,
   "pad_token": "[PAD]",
-  "padding_side": "right",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }