Trained with Unsloth

config.json

@@ -1,3 +1,31 @@
 {
-    "model_type": "llama"
-}
+  "_name_or_path": "unsloth/yi-1.5-6b-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.42.4",
+  "unsloth_version": "2024.7",
+  "use_cache": true,
+  "vocab_size": 64000
+}

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ffd5e200655288696cd4f278f596e1bd78ba4067c0ab1ae0a29e84d7080a49
-size 4932737763
+oid sha256:7b4cfa76c182579f7fb41c9e928aa6f01bbbd74f8c231ad36c3e7e34dbd1f933
+size 4932739043

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb1a3b817683e95e664486b9b11659facdc9ba183219ed896e43148149add849
-size 4976833026
+oid sha256:e1fc6e8ce5fbecda987a8b838046c0f49797d671bd4504c66bf9cc2b0a93e065
+size 4976834114

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4098579e170b826065dcdccdc845b382ff42200d7c0706da229710c7324ea6
-size 2212600770
+oid sha256:fddbc94aba13c1ea8f660bad76f18128047c305e7f6a71f21c9be2ff6e3ea6b6
+size 2212600834