Create README.md

README.md

@@ -0,0 +1,22 @@
+---
+datasets:
+- M4-ai/Rhino
+language:
+- en
+---
+# Model description
+The model was trained on approximately 200,000 examples from the M4-ai/Rhino dataset, with no examples omitted. It underwent eight checkpoints during training, with the second checkpoint identified as the best-performing one (after processing approximately 50,000 examples).
+
+This model has not been aligned with DPO. In the future, different repositories will be released that contain versions of this model aligned with DPO, using various datasets.
+
+# Evaluation
+Upon personal testing, the model demonstrates excellent performance in mathematics, history, and coding tasks.
+
+However, due to the model's requirement for the setting trust_remote_code=True, it cannot be submitted to the Open LLM Leaderboard. As a result, I will conduct my own evaluation of its capabilities.
+
+# Recommended prompt format
+```
+<|im_start|>system message <|im_end|> <|im_start|>user message <|im_end|> <|im_start|>assistant message <|im_end|>
+```
+
+I recommend passing eos_token="<|im_end|>" when initializing the tokenizer.