initial commit

.gitattributes

@@ -4,6 +4,7 @@
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,52 @@
 ---
 license: apache-2.0
+datasets:
+- bigcode/the-stack
+- bigcode/the-stack-v2
+- bigcode/starcoderdata
+- bigcode/commitpack
+library_name: transformers
+tags:
+- code
+base_model:
+- JetBrains/Mellum-4b-dpo-python
 ---
+
+# Model Description
+Mellum-4b-dpo-python is the third stage of our pipeline (after pretraining and SFT), trained with direct preference optimization on code-quality preferences to produce more readable, useful code.
+
+Pre-trained on over 4 trillion tokens with a context window of 8192 tokens across multiple programming languages, and then fine-tuned, Mellum-4b-dpo-python is tailored specifically for code completion in Python. 
+The model follows a LLaMA-style architecture with 4 billion parameters, making it efficient for both cloud inference (e.g., via vLLM) and local deployment (e.g., using llama.cpp or Ollama).
+
+Mellum was trained using Automatic Mixed Precision (AMP) with bf16 precision. 
+The uploaded version on Hugging Face retains the bf16 format for public use.
+
+Designed for integration into professional developer tooling (e.g., intelligent code suggestions in IDEs), AI-powered coding assistants, and research on code understanding and generation, Mellum is also well-suited for educational applications and fine-tuning experiments.
+
+# Limitations
+- Biases: May reflect biases present in public codebases. For example it will likely produce code which is similar in style to the open-source repositories.
+- Security: Code suggestions should not be assumed to be secure or free of vulnerabilities.
+- Format: This model is suitable mostly for FIM Completion objective with context's files.
+
+# Sample Usage
+Here are examples of how to run and sample from the model.
+
+## Fill-in-the-middle example
+
+```bash
+llama-cli -m mellum-4b-dpo-python.Q8_0.gguf --temp 0 -p $'<filename>main.py\n<fim_suffix><fim_prefix>def fibonacci(n):\n    <fim_middle>'
+```
+
+# Citation
+If you use this model, please cite:
+
+```bibtex
+@misc{Mellum-4b-dpo-python,
+  title     = {Mellum-4b-dpo-python},
+  author    = {Pavlichenko, Nikita and Nazarov, Iurii and Dolgov, Ivan and Garanina, Ekaterina and Lasocki, Karol and Reshetnikova, Julia and Boitsov, Sergei and Bondyrev, Ivan and Karaeva, Dariia and Sheptyakov, Maksim and Ustalov, Dmitry and Mukhin, Artem and Proshev, Semyon and Abramov, Nikita and Kolomyttseva, Olga and Lysaniuk, Kseniia and Zavidnyi, Ilia and Semenkin, Anton and Tankov, Vladislav and Sazanovich, Uladzislau},
+  year      = {2025},
+}
+```
+
+# Contact
+For questions, collaborations and requests reach us out via mellum@jetbrains.com

mellum-4b-dpo-python.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52de6d65dfa44e02ffdd15ec9905548e38c9732ae6c43fb17d5a1adce810cf5
+size 4274519520