(Trained with Unsloth)

config.json

@@ -1,3 +1,39 @@
 {
-    "model_type": "llama"
-}
+  "_name_or_path": "unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "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": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.3.14",
+  "use_cache": true,
+  "vocab_size": 128256
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85400d93a93aca12c7bfbd74d91745d76ce2f7a33be4a8a4e116916e8cc554fb
+oid sha256:dd354d53cf7066362cc51cc9f397bd8759d8027f249e6d6204e1e743a80e86b6
 size 2471678098

tokenizer_config.json

@@ -2061,7 +2061,7 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
 }