GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
JetBrains
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
JetBrains
Model Tree
JetBrains/Mellum-4b-sft-all
Input Modalities
Output Modalities
Supported Functionality
python
import jsonfrom transformers import AutoTokenizer, AutoModelForCausalLM example = """<filename>Utils.ktpackage utils fun multiply(x: Int, y: Int): Int { return x * y} <filename>Config.ktpackage config object Config { const val DEBUG = true const val MAX_VALUE = 100} <filename>Example.kt<fim_suffix>fun main() { val result = calculateSum(5, 10) println(result)}<fim_prefix>fun calculateSum(a: Int, b: Int): Int {<fim_middle>""" tokenizer = AutoTokenizer.from_pretrained('JetBrains/Mellum-4b-dpo-all')model = AutoModelForCausalLM.from_pretrained('JetBrains/Mellum-4b-dpo-all')encoded_input = tokenizer(example, return_tensors='pt', return_token_type_ids=False)out = model.generate( **encoded_input, max_new_tokens=100,)If you use this model, please cite:
bibtex
@misc{Mellum-4b-dpo-all, title = {Mellum-4b-dpo-all}, 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},}For questions, collaborations and requests reach us out via mellum@jetbrains.com
import jsonfrom transformers import AutoTokenizer, AutoModelForCausalLM example = """<filename>Utils.ktpackage utils fun multiply(x: Int, y: Int): Int { return x * y} <filename>Config.ktpackage config object Config { const val DEBUG = true const val MAX_VALUE = 100} <filename>Example.kt<fim_suffix>fun main() { val result = calculateSum(5, 10) println(result)}<fim_prefix>fun calculateSum(a: Int, b: Int): Int {<fim_middle>""" tokenizer = AutoTokenizer.from_pretrained('JetBrains/Mellum-4b-dpo-all')model = AutoModelForCausalLM.from_pretrained('JetBrains/Mellum-4b-dpo-all')encoded_input = tokenizer(example, return_tensors='pt', return_token_type_ids=False)out = model.generate( **encoded_input, max_new_tokens=100,)