Trained with Unsloth

README.md

@@ -1,3 +1,7 @@
 ---
 library_name: transformers
----
+tags:
+- unsloth
+- trl
+- sft
+---

config.json

@@ -11,19 +11,25 @@
   "hidden_size": 192,
   "initializer_range": 0.02,
   "intermediate_size": 1024,
-  "max_position_embeddings": 1024,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 2,
   "num_hidden_layers": 1,
   "num_key_value_heads": 1,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
+  "rope_scaling": {
+    "factor": 2.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.51.3",
+  "unsloth_version": "2025.4.4",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
   "transformers_version": "4.51.3"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b84b1446e4b9aa9b2a09f1175a58870ee6692cfed26cd47fa3ae8db0bf60f4
+size 25982955